Merge branch 'main' into docs/add-new-committers

Correct yongxiang mapping in the diffusion cache ownership list.

Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

.buildkite/amd/test-amd-merge.yml

@@ -1,233 +0,0 @@
-env:
-  VLLM_WORKER_MULTIPROC_METHOD: spawn
-  HF_HUB_DOWNLOAD_TIMEOUT: 300
-  HF_HUB_ETAG_TIMEOUT: 60
-
-steps:
-
-- group: ":card_index_dividers: Simple Test"
-  steps:
-    - label: "Simple · Diffusion & Model Executor Test (1/2)"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      timeout_in_minutes: 70
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_ROCM_USE_AITER=0
-        # ignore test_teacache_extractors.py because it use rocm gemm kernel from vLLM
-        # that is not supported on CPU
-        # CPU tests on ROCm gpu machines are very slow, so we give them more time.
-        - "timeout 60m pytest -sv tests/diffusion -m 'core_model and cpu' --ignore=tests/diffusion/cache/test_teacache_extractors.py --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-
-    - label: "Simple · Diffusion & Model Executor Test (2/2)"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      timeout_in_minutes: 70
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_ROCM_USE_AITER=0
-        # CPU tests on ROCm gpu machines are very slow, so we give them more time.
-        - "timeout 60m pytest -sv tests/model_executor -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-
-    - label: "Simple · Other Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      timeout_in_minutes: 50
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_ROCM_USE_AITER=0
-        # ignore test_teacache_extractors.py because it use rocm gemm kernel from vLLM
-        # that is not supported on CPU
-        - "timeout 40m pytest -sv tests/diffusion tests/model_executor -m 'core_model and cpu' --ignore=tests/diffusion/cache/test_teacache_extractors.py --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-
-- group: ":card_index_dividers: Diffusion Test"
-  steps:
-    - label: "Diffusion · LoRA Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - timeout 20m pytest -s -v tests/diffusion/lora/test_images_generations_lora.py
-
-    - label: "Diffusion Model CPU offloading Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_LOGGING_LEVEL=DEBUG
-        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-        - |
-          timeout 20m bash -c '
-            set +e
-            pytest -s -v tests/diffusion/offloader/test_diffusion_cpu_offload.py
-            EXIT1=\$?
-            pytest -s -v tests/diffusion/offloader/test_diffusion_layerwise_offload.py
-            EXIT2=\$?
-            exit \$((EXIT1 | EXIT2))
-          '
-
-    - label: "Diffusion Sequence Parallelism Test (Need 4 GPUs)"
-      agent_pool: mi325_4
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_LOGGING_LEVEL=DEBUG
-        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-        - timeout 20m pytest -s -v tests/diffusion/distributed/test_sequence_parallel.py
-        - timeout 20m pytest -s -v tests/diffusion/distributed/test_ulysses_uaa_perf.py
-
-    # merge-only tests
-    - label: "Diffusion Tensor Parallelism Test"
-      agent_pool: mi325_2
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - pytest -s -v tests/diffusion/distributed/test_tensor_parallel.py
-
-    - label: "Diffusion Model Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - timeout 30m pytest -s -v tests/e2e/offline_inference/test_z_image.py
-
-    - label: "Diffusion GPU Worker Test"
-      agent_pool: mi325_2
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - timeout 20m pytest -s -v tests/diffusion/test_diffusion_worker.py
-
-    - label: "Diffusion · Wan22 Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - |
-          timeout 40m bash -c "
-            export VLLM_IMAGE_FETCH_TIMEOUT=60
-            pytest -s -v tests/e2e/offline_inference/test_wan22_t2v.py tests/e2e/online_serving/test_wan22_t2v.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model'
-          "
-
-## ISSUE depends on `diffusers` package: https://github.com/huggingface/diffusers/issues/13274
-# - label: "Audio Generation Model Test"
-#   agent_pool: mi325_1
-#   depends_on: amd-build
-#   mirror_hardwares: [amdproduction]
-#   grade: Blocking
-#   commands:
-#     - export GPU_ARCHS=gfx942
-#     - export VLLM_LOGGING_LEVEL=DEBUG
-#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-#     - timeout 20m pytest -s -v tests/e2e/offline_inference/test_stable_audio_expansion.py -m "advanced_model and diffusion and L4" --run-level advanced_model
-
-- label: "Engine Test"
-  agent_pool: mi325_1
-  depends_on: amd-build
-  mirror_hardwares: [amdproduction]
-  grade: Blocking
-  commands:
-    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-    - timeout 20m pytest -s -v tests/engine/test_async_omni_engine_abort.py
-
-# This is from test-nightly.yml.
-# This model seems to be important, so I am trying to run it here.
-# Since this is from test-nightly.yml,
-# I keep this non-blocking.
-- group: ":card_index_dividers: E2E Test"
-  steps:
-    - label: "Omni Model Test Qwen2-5-Omni"
-      agent_pool: mi325_4
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      commands:
-        - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-        - pytest -s -v tests/e2e/*/test_qwen2_5_omni_expansion.py --run-level "core_model"
-
-    - label: "Omni Model Test Qwen3-Omni"
-      agent_pool: mi325_2
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-        - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-
-    - label: "Qwen3-TTS CustomVoice E2E Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - |
-          timeout 50m bash -c '
-            export VLLM_LOGGING_LEVEL=DEBUG
-            export VLLM_WORKER_MULTIPROC_METHOD=spawn
-            export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-            pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py tests/e2e/offline_inference/test_qwen3_tts_customvoice.py -m "advanced_model" --run-level "advanced_model"
-          '
-
-    - label: "Qwen3-TTS Base E2E Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      timeout_in_minutes: 50
-      commands:
-        - |
-          timeout 40m bash -c '
-            export VLLM_LOGGING_LEVEL=DEBUG
-            export VLLM_WORKER_MULTIPROC_METHOD=spawn
-            export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-            pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py tests/e2e/offline_inference/test_qwen3_tts_base.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-          '
-
-# TODO: Bagel test on ROCm is very unstable. @tjtanaa
-# Need to debug before reneable numerical changes across large PRs
-# # split Bagel Model Test with H100 (Real Weights) into three tests
-# - label: "Bagel Text2Img Model Test (1/3)"
-#   agent_pool: mi325_1
-#   depends_on: amd-build
-#   mirror_hardwares: [amdproduction]
-#   grade: Blocking
-#   commands:
-#     - export GPU_ARCHS=gfx942
-#     - export VLLM_LOGGING_LEVEL=DEBUG
-#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
-#     - timeout 30m pytest -s -v tests/e2e/offline_inference/test_bagel.py -m "advanced_model" --run-level "advanced_model" -k "shared_memory" -k "rocm"
-
-# - label: "Bagel Img2Img Model Test (2/3)"
-#   agent_pool: mi325_1
-#   depends_on: amd-build
-#   mirror_hardwares: [amdproduction]
-#   grade: Blocking
-#   commands:
-#     - export GPU_ARCHS=gfx942
-#     - export VLLM_LOGGING_LEVEL=DEBUG
-#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
-#     - timeout 30m pytest -s -v tests/e2e/offline_inference/test_bagel.py -m "advanced_model" --run-level "advanced_model" -k "rocm"
-
-# - label: "Bagel Online Serving Test (3/3)"
-#   agent_pool: mi325_1
-#   depends_on: amd-build
-#   mirror_hardwares: [amdproduction]
-#   grade: Blocking
-#   commands:
-#     - export GPU_ARCHS=gfx942
-#     - export VLLM_IMAGE_FETCH_TIMEOUT=60
-#     - export VLLM_LOGGING_LEVEL=DEBUG
-#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
-#     - timeout 40m pytest -s -v tests/e2e/online_serving/test_bagel.py -m "advanced_model" --run-level "advanced_model" -k "rocm"

.buildkite/amd/test-amd-ready.yml

@@ -1,223 +0,0 @@
-env:
-  VLLM_WORKER_MULTIPROC_METHOD: spawn
-  HF_HUB_DOWNLOAD_TIMEOUT: 300
-  HF_HUB_ETAG_TIMEOUT: 60
-
-steps:
-
-- group: ":card_index_dividers: Simple Test"
-  steps:
-    - label: "Simple · Diffusion & Model Executor Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_ROCM_USE_AITER=0
-        # ignore test_teacache_extractors.py because it use rocm gemm kernel from vLLM
-        # that is not supported on CPU
-        - "timeout 40m pytest -sv tests/diffusion tests/model_executor -m 'core_model and cpu' --ignore=tests/diffusion/cache/test_teacache_extractors.py --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-
-    - label: "Simple · Other Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_ROCM_USE_AITER=0
-        # ignore test_teacache_extractors.py because it use rocm gemm kernel from vLLM
-        # that is not supported on CPU
-        - "timeout 40m pytest -sv tests/diffusion tests/model_executor -m 'core_model and cpu' --ignore=tests/diffusion/cache/test_teacache_extractors.py --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-
-- label: "Custom Pipeline Test"
-  agent_pool: mi325_1
-  depends_on: amd-build
-  mirror_hardwares: [amdproduction]
-  grade: Blocking
-  commands:
-    - timeout 20m pytest -s -v tests/e2e/features/custom_pipeline/ -m "core_model"
-
-
-- label: "Voxtral TTS CUDA Unit Test"
-  agent_pool: mi325_1
-  depends_on: amd-build
-  mirror_hardwares: [amdproduction]
-  grade: Blocking
-  commands:
-    - timeout 10m pytest -s -v tests/model_executor/models/voxtral_tts/test_cuda_graph_acoustic_transformer.py
-
-- group: ":card_index_dividers: Diffusion Test"
-  steps:
-    - label: "Diffusion · Batch Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - timeout 20m pytest -sv tests/diffusion/batching -m 'core_model and cuda' --run-level "core_model"
-
-    - label: "Diffusion · Offloader Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_LOGGING_LEVEL=DEBUG
-        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-        - |
-          timeout 20m bash -c '
-            set +e
-            pytest -s -v tests/diffusion/offloader/test_diffusion_cpu_offload.py
-            EXIT1=\$?
-            pytest -s -v tests/diffusion/offloader/test_diffusion_layerwise_offload.py
-            EXIT2=\$?
-            exit \$((EXIT1 | EXIT2))
-          '
-
-    - label: "Diffusion · Cache Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export GPU_ARCHS=gfx942
-        - export VLLM_LOGGING_LEVEL=DEBUG
-        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-        - timeout 15m pytest -s -v -m "core_model and cache and diffusion and not distributed_cuda and L4"
-
-    - label: "Diffusion Sequence Parallelism Test"
-      agent_pool: mi325_2
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_LOGGING_LEVEL=DEBUG
-        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-        - timeout 20m pytest -s -v tests/diffusion/distributed/test_sequence_parallel.py -m core_model
-
-    - label: "Diffusion GPU Worker Test"
-      agent_pool: mi325_2
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - timeout 20m pytest -s -v tests/diffusion/test_diffusion_worker.py
-
-    - label: "Diffusion · Model Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - timeout 15m pytest -sv tests/diffusion/models/ -m 'core_model and cuda' --run-level "core_model"
-
-    - label: "Diffusion · Wan22 Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - |
-          timeout 40m bash -c "
-            export VLLM_TEST_CLEAN_GPU_MEMORY=1
-            export VLLM_IMAGE_FETCH_TIMEOUT=60
-            pytest -s -v tests/e2e/online_serving/test_wan22_t2v.py -m 'core_model' --run-level 'core_model'
-          "
-
-## ISSUE depends on `diffusers` package: https://github.com/huggingface/diffusers/issues/13274
-# - label: "Audio Generation Model Test"
-#   agent_pool: mi325_1
-#   depends_on: amd-build
-#   mirror_hardwares: [amdproduction]
-#   grade: Blocking
-#   commands:
-#     - export GPU_ARCHS=gfx942
-#     - export VLLM_LOGGING_LEVEL=DEBUG
-#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-#     - timeout 20m pytest -s -v tests/e2e/offline_inference/test_stable_audio_expansion.py -m "advanced_model and diffusion and L4" --run-level advanced_model
-
-- label: "Engine Test"
-  agent_pool: mi325_1
-  depends_on: amd-build
-  mirror_hardwares: [amdproduction]
-  grade: Blocking
-  commands:
-    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-    - |
-      timeout 15m bash -c '
-              pytest -s -v tests/engine/test_async_omni_engine_abort.py
-      '
-
-# - label: "Omni Model Test Qwen3-Omni"
-#   agent_pool: mi325_2
-#   depends_on: amd-build
-#   mirror_hardwares: [amdproduction]
-#   grade: Blocking
-#   commands:
-#     - export VLLM_LOGGING_LEVEL=DEBUG
-#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-#     - timeout 10m pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
-#     - timeout 20m pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m "core_model" --run-level "core_model"
-
-- group: ":card_index_dividers: E2E Test"
-  steps:
-    - label: "Qwen3-TTS E2E Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - export VLLM_LOGGING_LEVEL=DEBUG
-        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-        - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-        - timeout 30m pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m "core_model" --run-level "core_model"
-
-    - label: "CosyVoice3-TTS E2E Test"
-      agent_pool: mi325_1
-      depends_on: amd-build
-      mirror_hardwares: [amdproduction]
-      grade: Blocking
-      commands:
-        - |
-          timeout 20m bash -c '
-            pytest -s -v tests/e2e/online_serving/test_cosyvoice3_tts_expansion.py -m "slow" --run-level "core_model"
-          '
-
-# TODO: Bagel test on ROCm is very unstable. @tjtanaa
-# Need to debug before reneable numerical changes across large PRs
-# - label: "Bagel Text2Img Model Test"
-#   agent_pool: mi325_1
-#   depends_on: amd-build
-#   mirror_hardwares: [amdproduction]
-#   grade: Blocking
-#   commands:
-#     - export GPU_ARCHS=gfx942
-#     - export VLLM_LOGGING_LEVEL=DEBUG
-#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
-#     - timeout 30m pytest -s -v tests/e2e/offline_inference/test_bagel.py -m "core_model" --run-level "core_model" -k "rocm"
-
-# - label: "Bagel Img2Img Model Test"
-#   agent_pool: mi325_1
-#   depends_on: amd-build
-#   mirror_hardwares: [amdproduction]
-#   grade: Blocking
-#   commands:
-#     - export GPU_ARCHS=gfx942
-#     - export VLLM_LOGGING_LEVEL=DEBUG
-#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
-#     - timeout 30m pytest -s -v tests/e2e/offline_inference/test_bagel.py -m "core_model" --run-level "core_model" -k "rocm"
-
-# - label: "Bagel Online Serving Test"
-#   agent_pool: mi325_1
-#   depends_on: amd-build
-#   mirror_hardwares: [amdproduction]
-#   grade: Blocking
-#   commands:
-#     - export GPU_ARCHS=gfx942
-#     - export VLLM_IMAGE_FETCH_TIMEOUT=60
-#     - export VLLM_LOGGING_LEVEL=DEBUG
-#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
-#     - timeout 40m pytest -s -v tests/e2e/online_serving/test_bagel.py -m "core_model" --run-level "core_model" -k "rocm"

.buildkite/amd/test-template-amd-omni.j2

@@ -1,141 +0,0 @@
-{# vllm-omni customized version
-   Based on: https://github.com/vllm-project/ci-infra/blob/main/buildkite/test-template-amd.j2
-   Last synced: 2025-12-15
-   Modifications: Removed unused CUDA/NVIDIA logic, keeping only AMD tests
-#}
-{% set docker_image_amd = "rocm/vllm-omni:$BUILDKITE_COMMIT" %}
-{% set default_working_dir = "/app/vllm-omni" %}
-
-{% if env %}
-env:
-{% for name in env %}
-  {{ name }}: "{{ env[name] }}"
-{% endfor %}
-{% endif %}
-steps:
-  - group: "AMD Tests"
-    depends_on: ~
-    steps:
-      - label: "AMD: :docker: build image"
-        depends_on: ~
-        soft_fail: false
-        commands:
-          - "docker build -f docker/Dockerfile.rocm -t {{ docker_image_amd }} --target test --build-arg ARG_PYTORCH_ROCM_ARCH=gfx942 --progress plain ."
-          - "docker push {{ docker_image_amd }}"
-        key: "amd-build"
-        env:
-          DOCKER_BUILDKIT: "1"
-        retry:
-          automatic:
-            - exit_status: -1  # Agent was lost
-              limit: 2
-            - exit_status: -10  # Agent was lost
-              limit: 2
-            - exit_status: 128  # Git connectivity issues
-              limit: 2
-            - exit_status: 1  # Machine occasionally fail
-              limit: 1
-        agents:
-          queue: amd-cpu
-
-{% for step_group in steps %}
-{% if step_group.group %}
-  - group: "{{ step_group.group }}"
-{% if step_group.depends_on %}
-    depends_on: {{ step_group.depends_on }}
-{% endif %}
-    steps:
-{% for step in step_group.steps %}
-{% if step.mirror_hardwares and mirror_hw in step.mirror_hardwares %}
-      - label: "{{ step.agent_pool }}: {{ step.label }}"
-        depends_on: amd-build
-        agents:
-          {% if step.agent_pool %}
-          queue: amd_{{ step.agent_pool }}
-          {% else %}
-          queue: amd_mi325_1
-          {% endif %}
-{% set cmd_body = (step.command or (step.commands | join("\n"))) | trim %}
-{% set indented_cmd = cmd_body | replace("\n", "\n            ") %}
-        command: bash .buildkite/amd/scripts/run-amd-test.sh
-        env:
-          DOCKER_BUILDKIT: "1"
-{% if step.env %}
-{% for name in step.env %}
-          {{ name }}: "{{ step.env[name] }}"
-{% endfor %}
-{% endif %}
-          TEST_COMMAND: |-
-            (command rocm-smi || true) && cd {{ (step.working_dir or default_working_dir) | safe }}
-{% if env %}
-{% for name in env %}
-            export {{ name }}="{{ env[name] }}"
-{% endfor %}
-{% endif %}
-{% if step.env %}
-{% for name in step.env %}
-            export {{ name }}="{{ step.env[name] }}"
-{% endfor %}
-{% endif %}
-{% if "mi250" in step.agent_pool %}
-            python3 -m pip uninstall -y amd-aiter
-{% endif %}
-            {{ indented_cmd | safe }}
-        priority: 100
-        {% if step.timeout_in_minutes %}
-        timeout_in_minutes: {{ step.timeout_in_minutes }}
-        {% endif %}
-        {% if step.grade and step.grade == "Blocking" %}
-        soft_fail: false
-        {% else %}
-        soft_fail: true
-        {% endif%}
-{% endif %}
-{% endfor %}
-{% elif step_group.mirror_hardwares and mirror_hw in step_group.mirror_hardwares %}
-{% set step = step_group %}
-  - label: "{{ step.agent_pool }}: {{ step.label }}"
-    depends_on: amd-build
-    agents:
-      {% if step.agent_pool %}
-      queue: amd_{{ step.agent_pool }}
-      {% else %}
-      queue: amd_mi325_1
-      {% endif %}
-{% set cmd_body = (step.command or (step.commands | join("\n"))) | trim %}
-{% set indented_cmd = cmd_body | replace("\n", "\n        ") %}
-    command: bash .buildkite/amd/scripts/run-amd-test.sh
-    env:
-      DOCKER_BUILDKIT: "1"
-{% if step.env %}
-{% for name in step.env %}
-      {{ name }}: "{{ step.env[name] }}"
-{% endfor %}
-{% endif %}
-      TEST_COMMAND: |-
-        (command rocm-smi || true) && cd {{ (step.working_dir or default_working_dir) | safe }}
-{% if env %}
-{% for name in env %}
-        export {{ name }}="{{ env[name] }}"
-{% endfor %}
-{% endif %}
-{% if step.env %}
-{% for name in step.env %}
-        export {{ name }}="{{ step.env[name] }}"
-{% endfor %}
-{% endif %}
-{% if "mi250" in step.agent_pool %}
-        python3 -m pip uninstall -y amd-aiter
-{% endif %}
-        {{ indented_cmd | safe }}
-    priority: 100
-    {% if step.timeout_in_minutes %}
-    timeout_in_minutes: {{ step.timeout_in_minutes }}
-    {% endif %}
-    {% if step.grade and step.grade == "Blocking" %}
-    soft_fail: false
-    {% else %}
-    soft_fail: true
-    {% endif%}
-{% endif %}
-{% endfor %}

.buildkite/bootstrap-amd-omni.sh

@@ -6,8 +6,6 @@
 
 set -euo pipefail
 
-source .buildkite/common/scripts/resolve_skip_ci.sh
-
 if [[ -z "${RUN_ALL:-}" ]]; then
     RUN_ALL=0
 fi
@@ -24,6 +22,10 @@ if [[ -z "${AMD_MIRROR_HW:-}" ]]; then
     AMD_MIRROR_HW="amdproduction"
 fi
 
+if [[ -z "${DOCS_ONLY_DISABLE:-}" ]]; then
+    DOCS_ONLY_DISABLE=0
+fi
+
 fail_fast() {
     DISABLE_LABEL="ci-no-fail-fast"
     # If BUILDKITE_PULL_REQUEST != "false", then we check the PR labels using curl and jq
@@ -54,6 +56,88 @@ check_run_all_label() {
     fi
 }
 
+is_docs_only_change() {
+    local file_path
+    local has_any=0
+
+    while IFS= read -r file_path; do
+        [[ -z "${file_path}" ]] && continue
+        has_any=1
+
+        if [[ "${file_path}" == docs/* ]]; then
+            continue
+        fi
+        if [[ "${file_path}" == *.md ]]; then
+            continue
+        fi
+        if [[ "${file_path}" == "mkdocs.yml" ]]; then
+            continue
+        fi
+        return 1
+    done
+
+    [[ "${has_any}" -eq 1 ]]
+}
+
+resolve_skip_ci() {
+    local is_pr_build=0
+    local files
+    local base_branch base_ref
+
+    if [[ "${BUILDKITE_PULL_REQUEST:-false}" != "false" && -n "${BUILDKITE_PULL_REQUEST:-}" ]]; then
+        is_pr_build=1
+    fi
+
+    if [[ "${is_pr_build}" -eq 1 ]]; then
+        base_branch="${BUILDKITE_PULL_REQUEST_BASE_BRANCH:-main}"
+        if ! git rev-parse --verify "origin/${base_branch}" >/dev/null 2>&1; then
+            echo "resolve_skip_ci: origin/${base_branch} not found locally; trying fetch" >&2
+            git fetch --depth=200 origin "${base_branch}" >/dev/null 2>&1 || true
+        fi
+
+        base_ref=""
+        if git rev-parse --verify "origin/${base_branch}" >/dev/null 2>&1; then
+            base_ref="origin/${base_branch}"
+        elif git rev-parse --verify "${base_branch}" >/dev/null 2>&1; then
+            base_ref="${base_branch}"
+        else
+            echo "resolve_skip_ci: cannot resolve PR base ${base_branch}; skip-ci=0" >&2
+            echo -n 0
+            return 0
+        fi
+
+        if ! files="$(git diff --name-only "${base_ref}...${BUILDKITE_COMMIT}" 2>/dev/null)"; then
+            echo "resolve_skip_ci: failed to compute PR changed files; skip-ci=0" >&2
+            echo -n 0
+            return 0
+        fi
+    elif [[ "${BUILDKITE_BRANCH:-}" == "main" ]]; then
+        if ! git rev-parse --verify "${BUILDKITE_COMMIT}^" >/dev/null 2>&1; then
+            echo "resolve_skip_ci: commit has no parent on main; skip-ci=0" >&2
+            echo -n 0
+            return 0
+        fi
+        if ! files="$(git diff --name-only "${BUILDKITE_COMMIT}^..${BUILDKITE_COMMIT}" 2>/dev/null)"; then
+            echo "resolve_skip_ci: failed to compute main changed files; skip-ci=0" >&2
+            echo -n 0
+            return 0
+        fi
+    else
+        echo "resolve_skip_ci: not PR/main build; skip-ci=0" >&2
+        echo -n 0
+        return 0
+    fi
+
+    if is_docs_only_change <<< "${files}"; then
+        echo "resolve_skip_ci: docs-only change detected; skip-ci=1" >&2
+        echo -n 1
+        return 0
+    fi
+
+    echo "resolve_skip_ci: non-doc changes detected; skip-ci=0" >&2
+    echo -n 0
+}
+
 if [[ -z "${COV_ENABLED:-}" ]]; then
     COV_ENABLED=0
 fi
@@ -70,14 +154,14 @@ upload_pipeline() {
     fi
 
     # Use local template file for vllm-omni
-    cp .buildkite/amd/test-template-amd-omni.j2 .buildkite/amd/test-template.j2
+    cp .buildkite/test-template-amd-omni.j2 .buildkite/test-template.j2
 
 
     # (WIP) Use pipeline generator instead of jinja template
-    if [ -e ".buildkite/amd/pipeline_generator/pipeline_generator.py" ]; then
+    if [ -e ".buildkite/pipeline_generator/pipeline_generator.py" ]; then
         python -m pip install click pydantic
-        python .buildkite/amd/pipeline_generator/pipeline_generator.py --run_all=$RUN_ALL --list_file_diff="$LIST_FILE_DIFF" --nightly="$NIGHTLY" --mirror_hw="$AMD_MIRROR_HW"
+        python .buildkite/pipeline_generator/pipeline_generator.py --run_all=$RUN_ALL --list_file_diff="$LIST_FILE_DIFF" --nightly="$NIGHTLY" --mirror_hw="$AMD_MIRROR_HW"
-        buildkite-agent pipeline upload .buildkite/amd/pipeline.yaml
+        buildkite-agent pipeline upload .buildkite/pipeline.yaml
         exit 0
     fi
     echo "List file diff: $LIST_FILE_DIFF"
@@ -87,7 +171,7 @@ upload_pipeline() {
 
     FAIL_FAST=$(fail_fast)
 
-    cd .buildkite/amd
+    cd .buildkite
 
     # Select test definition file: merge suite for main, ready suite for PRs.
     # For debugging, DEBUG_TEST_YAML can override the selection — accepts
@@ -98,7 +182,7 @@ upload_pipeline() {
                 TEST_YAML="test-amd-merge.yml"
                 ;;
             ready)
-                TEST_YAML="test-amd-ready.yml"
+                TEST_YAML="test-amd-ready.yaml"
                 ;;
             *)
                 echo "ERROR: DEBUG_TEST_YAML must be 'merge' or 'ready', got '$DEBUG_TEST_YAML'" >&2
@@ -109,7 +193,7 @@ upload_pipeline() {
     elif [[ $BUILDKITE_BRANCH == "main" ]]; then
         TEST_YAML="test-amd-merge.yml"
     else
-        TEST_YAML="test-amd-ready.yml"
+        TEST_YAML="test-amd-ready.yaml"
     fi
 
     (
@@ -150,13 +234,23 @@ if [[ $BUILDKITE_BRANCH == "main" ]]; then
     file_diff=$(get_diff_main)
 fi
 
-# Early exit: unified skip-ci (docs / skip marks) and CI-yaml-only level targeting.
+# ----------------------------------------------------------------------
-if [[ $BUILDKITE_BRANCH == "main" ]]; then
+# Early exit start: skip pipeline if conditions are met
-    gate_bootstrap_ci amd l3
+# ----------------------------------------------------------------------
-else
+
-    gate_bootstrap_ci amd l2
+# Match CUDA Buildkite skip-ci behavior for docs/markdown-only changes.
+if [[ "${DOCS_ONLY_DISABLE}" != "1" ]]; then
+    SKIP_CI="$(resolve_skip_ci)"
+    if [[ "${SKIP_CI}" == "1" ]]; then
+        echo "[docs-only] Docs/markdown-only changes detected. Exiting before pipeline upload."
+        exit 0
+    fi
 fi
 
+# ----------------------------------------------------------------------
+# Early exit end
+# ----------------------------------------------------------------------
+
 patterns=(
     "docker/Dockerfile"
     "CMakeLists.txt"

.buildkite/bootstrap-intel-omni.sh

@@ -0,0 +1,51 @@
+#!/bin/bash
+# vllm-omni Intel bootstrap
+# Uses static pipeline-intel.yaml for Intel XPU tests
+# Based on: bootstrap-amd-omni.sh
+
+set -euo pipefail
+
+if [[ -z "${DOCS_ONLY_DISABLE:-}" ]]; then
+    DOCS_ONLY_DISABLE=0
+fi
+
+upload_pipeline() {
+    echo "--- 🛠 Preparing Intel pipeline"
+    buildkite-agent pipeline upload .buildkite/pipeline-intel.yaml
+}
+
+get_diff() {
+    $(git add .)
+    echo $(git diff --name-only --diff-filter=ACMDR $(git merge-base origin/main HEAD))
+}
+
+get_diff_main() {
+    $(git add .)
+    echo $(git diff --name-only --diff-filter=ACMDR HEAD~1)
+}
+
+file_diff=$(get_diff)
+if [[ $BUILDKITE_BRANCH == "main" ]]; then
+    file_diff=$(get_diff_main)
+fi
+
+# ----------------------------------------------------------------------
+# Early exit: skip pipeline if all changed files are under docs/
+# ----------------------------------------------------------------------
+if [[ "${DOCS_ONLY_DISABLE}" != "1" ]] && [[ -n "${file_diff:-}" ]]; then
+    docs_only=1
+    while IFS= read -r f; do
+        [[ -z "$f" ]] && continue
+        if [[ "$f" != docs/* ]]; then
+            docs_only=0
+            break
+        fi
+    done < <(printf '%s\n' "$file_diff" | tr ' ' '\n' | tr -d '\r')
+
+    if [[ "$docs_only" -eq 1 ]]; then
+        buildkite-agent annotate ":memo: CI skipped — docs only" --style "info"
+        exit 0
+    fi
+fi
+
+upload_pipeline

.buildkite/common/ci_mirror_hardwares.yml

@@ -1,239 +0,0 @@
-# Uploader-only hardware presets for CUDA / NPU test YAML.
-# Referenced as ``mirror_hardwares: l4_1`` on a step; ``upload_pipeline.py`` expands to
-# ``agents`` (+ optional top-level ``image`` for NPU) + ``plugins``, then strips
-# ``mirror_hardwares`` before Buildkite upload.
-#
-# CUDA naming: {chip}_{count}
-#   l4_1, l4_4, h100_1 … h100_4
-# NPU naming: {queue}_{resource_class}
-#   a2b3_npu_1  — ascend-a2b3, resource_class npu-1 (A2/B3 CI image)
-#   a2b3_npu_4  — ascend-a2b3, resource_class npu-4
-#   a3_npu_2    — ascend-a3, resource_class npu-2
-
-x-npu-k8s-plugins: &npu_k8s_plugins
-  - kubernetes:
-      podSpecPatch:
-        imagePullSecrets:
-          - name: swr-secret
-
-
-mirror_hardwares:
-  l4_1:
-    agents:
-      queue: gpu_1_queue
-    plugins:
-      - docker#v5.2.0:
-          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-          always-pull: true
-          propagate-environment: true
-          shm-size: "8gb"
-          environment:
-            - HF_HOME=/fsx/hf_cache
-            - HF_TOKEN
-          volumes:
-            - /fsx/hf_cache:/fsx/hf_cache
-
-  l4_4:
-    agents:
-      queue: gpu_4_queue
-    plugins:
-      - docker#v5.2.0:
-          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-          always-pull: true
-          propagate-environment: true
-          shm-size: "8gb"
-          environment:
-            - HF_HOME=/fsx/hf_cache
-            - HF_TOKEN
-          volumes:
-            - /fsx/hf_cache:/fsx/hf_cache
-
-  h100_1:
-    agents:
-      queue: mithril-h100-pool
-    plugins:
-      - kubernetes:
-          podSpec:
-            containers:
-              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-                resources:
-                  limits:
-                    nvidia.com/gpu: 1
-                volumeMounts:
-                  - name: devshm
-                    mountPath: /dev/shm
-                  - name: hf-cache
-                    mountPath: /root/.cache/huggingface
-                env:
-                  - name: HF_HOME
-                    value: /root/.cache/huggingface
-                  - name: HF_TOKEN
-                    valueFrom:
-                      secretKeyRef:
-                        name: hf-token-secret
-                        key: token
-            nodeSelector:
-              node.kubernetes.io/instance-type: gpu-h100-sxm
-            volumes:
-              - name: devshm
-                emptyDir:
-                  medium: Memory
-              - name: hf-cache
-                hostPath:
-                  path: /mnt/hf-cache
-                  type: DirectoryOrCreate
-
-  h100_2:
-    agents:
-      queue: mithril-h100-pool
-    plugins:
-      - kubernetes:
-          podSpec:
-            containers:
-              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-                resources:
-                  limits:
-                    nvidia.com/gpu: 2
-                volumeMounts:
-                  - name: devshm
-                    mountPath: /dev/shm
-                  - name: hf-cache
-                    mountPath: /root/.cache/huggingface
-                env:
-                  - name: HF_HOME
-                    value: /root/.cache/huggingface
-                  - name: HF_TOKEN
-                    valueFrom:
-                      secretKeyRef:
-                        name: hf-token-secret
-                        key: token
-            nodeSelector:
-              node.kubernetes.io/instance-type: gpu-h100-sxm
-            volumes:
-              - name: devshm
-                emptyDir:
-                  medium: Memory
-              - name: hf-cache
-                hostPath:
-                  path: /mnt/hf-cache
-                  type: DirectoryOrCreate
-
-  h100_3:
-    agents:
-      queue: mithril-h100-pool
-    plugins:
-      - kubernetes:
-          podSpec:
-            containers:
-              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-                resources:
-                  limits:
-                    nvidia.com/gpu: 3
-                volumeMounts:
-                  - name: devshm
-                    mountPath: /dev/shm
-                  - name: hf-cache
-                    mountPath: /root/.cache/huggingface
-                env:
-                  - name: HF_HOME
-                    value: /root/.cache/huggingface
-                  - name: HF_TOKEN
-                    valueFrom:
-                      secretKeyRef:
-                        name: hf-token-secret
-                        key: token
-            nodeSelector:
-              node.kubernetes.io/instance-type: gpu-h100-sxm
-            volumes:
-              - name: devshm
-                emptyDir:
-                  medium: Memory
-              - name: hf-cache
-                hostPath:
-                  path: /mnt/hf-cache
-                  type: DirectoryOrCreate
-
-  h100_4:
-    agents:
-      queue: mithril-h100-pool
-    plugins:
-      - kubernetes:
-          podSpec:
-            containers:
-              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-                resources:
-                  limits:
-                    nvidia.com/gpu: 4
-                volumeMounts:
-                  - name: devshm
-                    mountPath: /dev/shm
-                  - name: hf-cache
-                    mountPath: /root/.cache/huggingface
-                env:
-                  - name: HF_HOME
-                    value: /root/.cache/huggingface
-                  - name: HF_TOKEN
-                    valueFrom:
-                      secretKeyRef:
-                        name: hf-token-secret
-                        key: token
-            nodeSelector:
-              node.kubernetes.io/instance-type: gpu-h100-sxm
-            volumes:
-              - name: devshm
-                emptyDir:
-                  medium: Memory
-              - name: hf-cache
-                hostPath:
-                  path: /mnt/hf-cache
-                  type: DirectoryOrCreate
-
-  a2b3_npu_1:
-    agents:
-      queue: "ascend-a2b3"
-      resource_class: "npu-1"
-    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}"
-    plugins: *npu_k8s_plugins
-
-  a2b3_npu_4:
-    agents:
-      queue: "ascend-a2b3"
-      resource_class: "npu-4"
-    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}"
-    plugins: *npu_k8s_plugins
-
-
-  a2b3_npu_8:
-    agents:
-      queue: "ascend-a2b3"
-      resource_class: "npu-8"
-    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}"
-    plugins: *npu_k8s_plugins
-
-  a3_npu_2:
-    agents:
-      queue: "ascend-a3"
-      resource_class: "npu-2"
-    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a3"
-    plugins: *npu_k8s_plugins
-
-  a3_npu_4:
-    agents:
-      queue: "ascend-a3"
-      resource_class: "npu-4"
-    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a3"
-    plugins: *npu_k8s_plugins
-
-  a3_npu_8:
-    agents:
-      queue: "ascend-a3"
-      resource_class: "npu-8"
-    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a3"
-    plugins: *npu_k8s_plugins
-
-  a3_npu_16:
-    agents:
-      queue: "ascend-a3"
-      resource_class: "npu-16"
-    image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}-a3"
-    plugins: *npu_k8s_plugins

.buildkite/common/scripts/resolve_skip_ci.sh

@@ -1,23 +0,0 @@
-#!/usr/bin/env bash
-# Shared Buildkite skip-ci helpers for AMD / Intel bootstrap scripts.
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-SKIP_CI_PY="${SCRIPT_DIR}/skip_ci.py"
-
-# Resolve git diff once. Exit 0 when this bootstrap should stop uploading.
-# Decision details are logged by skip_ci.py; this helper only annotates skip-all.
-# Usage: gate_bootstrap_ci <platform> <l2|l3>
-gate_bootstrap_ci() {
-    local platform="$1"
-    local level="$2"
-    local kind
-    if kind="$(python3 "${SKIP_CI_PY}" gate "${platform}" "${level}")"; then
-        if [[ "${kind}" == "skip-all" ]]; then
-            buildkite-agent annotate \
-                ":memo: CI skipped — docs or pytest skip-mark changes only" \
-                --style "info" 2>/dev/null || true
-        fi
-        exit 0
-    fi
-}

.buildkite/common/scripts/skip_ci.py

@@ -1,617 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: Apache-2.0
-"""Shared Buildkite skip-ci and CI-YAML level targeting logic.
-
-``resolve_ci_decision(changed_files, ...)`` buckets explicit file lists (tests, dry-run).
-``resolve_ci_context_from_git()`` resolves git diff once and returns decision + changed files
-for Buildkite bootstrap / upload scripts.
-
-CLI (for bootstrap scripts; exit code is the signal):
-  python3 skip_ci.py gate <platform> <level>
-      Exit 0 when bootstrap should stop (skip-all, or that L2/L3 target is off).
-      Prints ``skip-all`` or ``skip-l23`` on stdout; logs the decision once.
-  python3 skip_ci.py check-skip-all
-      Exit 0 when only docs/skip-mark changes → bootstrap skips entire CI upload.
-  python3 skip_ci.py check-skip-l2-l3 <platform> <level>
-      Exit 0 when that L2/L3 pipeline should be skipped (CI config YAML-only diffs).
-  python3 skip_ci.py print-annotate
-      Print decision message for Buildkite annotation.
-"""
-
-from __future__ import annotations
-
-import argparse
-import os
-import re
-import subprocess
-import sys
-from dataclasses import dataclass, field, replace
-from pathlib import Path
-
-LOG = "[skip-ci]"
-ROOT = Path(__file__).resolve().parent.parent.parent.parent
-
-PLATFORMS = ("cuda", "amd", "intel", "npu")
-L23_LEVELS = frozenset({"l2", "l3"})
-
-L2_YAML_FILES: dict[str, str] = {
-    ".buildkite/cuda/test-ready.yml": "cuda",
-    ".buildkite/npu/test-npu-ready.yml": "npu",
-    ".buildkite/amd/test-amd-ready.yml": "amd",
-    ".buildkite/intel/pipeline-intel.yml": "intel",
-}
-
-L3_YAML_FILES: dict[str, str] = {
-    ".buildkite/cuda/test-merge.yml": "cuda",
-    ".buildkite/amd/test-amd-merge.yml": "amd",
-}
-
-L45_YAML_FILES: dict[str, str] = {
-    ".buildkite/cuda/test-nightly.yml": "cuda",
-    ".buildkite/cuda/test-weekly.yml": "cuda",
-    ".buildkite/npu/test-npu-nightly.yml": "npu",
-}
-
-
-def _empty_platform_buckets() -> dict[str, list[str]]:
-    return {platform: [] for platform in PLATFORMS}
-
-
-@dataclass(frozen=True)
-class CiDevice:
-    """Per-platform / per-level skip flags for yaml-gated bootstrap (``skip_l2_l3``)."""
-
-    skip_cuda_l2: bool = False
-    skip_cuda_l3: bool = False
-    skip_amd_l2: bool = False
-    skip_amd_l3: bool = False
-    skip_intel_l2: bool = False
-    skip_intel_l3: bool = False
-    skip_npu_l2: bool = False
-    skip_npu_l3: bool = False
-
-    def is_skip(self, platform: str, level: str) -> bool:
-        return bool(getattr(self, f"skip_{platform}_{level}", True))
-
-
-@dataclass
-class DiffBuckets:
-    """Changed files grouped by doc / skip-mark / CI yaml / other."""
-
-    docs: list[str] = field(default_factory=list)
-    skip_tests: list[str] = field(default_factory=list)
-    other: list[str] = field(default_factory=list)
-    l2: dict[str, list[str]] = field(default_factory=_empty_platform_buckets)
-    l3: dict[str, list[str]] = field(default_factory=_empty_platform_buckets)
-    l45: dict[str, list[str]] = field(default_factory=_empty_platform_buckets)
-
-    @property
-    def has_doc_changes(self) -> bool:
-        return bool(self.docs)
-
-    @property
-    def has_skip_test_changes(self) -> bool:
-        return bool(self.skip_tests)
-
-    @property
-    def has_other_changes(self) -> bool:
-        """Product code or paths outside skip-ci scope."""
-        return bool(self.other)
-
-    @property
-    def has_l23_yaml_changes(self) -> bool:
-        """At least one whitelisted L2/L3 CI yaml file changed."""
-        return any(self.l2[platform] or self.l3[platform] for platform in PLATFORMS)
-
-    @property
-    def has_l45_yaml_changes(self) -> bool:
-        """At least one whitelisted L4/L5 (nightly/weekly) CI yaml file changed."""
-        return any(self.l45[platform] for platform in PLATFORMS)
-
-    @property
-    def has_skip_ci_scope_changes(self) -> bool:
-        """At least one doc / skip-mark / whitelisted CI yaml change."""
-        return (
-            self.has_doc_changes or self.has_skip_test_changes or self.has_l23_yaml_changes or self.has_l45_yaml_changes
-        )
-
-    def l2_platforms(self) -> frozenset[str]:
-        return frozenset(platform for platform in PLATFORMS if self.l2[platform])
-
-    def l3_platforms(self) -> frozenset[str]:
-        return frozenset(platform for platform in PLATFORMS if self.l3[platform])
-
-
-@dataclass(frozen=True)
-class SkipL2L3Basis:
-    skip_all_l2: bool
-    skip_all_l3: bool
-
-    @classmethod
-    def from_buckets(cls, buckets: DiffBuckets) -> SkipL2L3Basis | None:
-        """L4/L5 yaml → skip both L2 and L3 (L2/L3 buckets may rescue).
-
-        Docs / skip-mark changes do not block this path; they are ignored for
-        L2/L3 targeting when CI YAML is also present.
-        """
-        if buckets.has_other_changes:
-            return None
-        if not buckets.has_l45_yaml_changes:
-            return None
-        return cls(
-            skip_all_l2=not buckets.l2_platforms(),
-            skip_all_l3=not buckets.l3_platforms(),
-        )
-
-
-@dataclass(frozen=True)
-class SkipL3Basis:
-    enable_l2_platforms: frozenset[str]
-
-    @classmethod
-    def from_buckets(cls, buckets: DiffBuckets) -> SkipL3Basis | None:
-        """L2 yaml changed → skip L3; keep L2 on touched platforms."""
-        platforms = buckets.l2_platforms()
-        if not platforms:
-            return None
-        return cls(enable_l2_platforms=platforms)
-
-
-@dataclass(frozen=True)
-class SkipL2Basis:
-    enable_l3_platforms: frozenset[str]
-
-    @classmethod
-    def from_buckets(cls, buckets: DiffBuckets) -> SkipL2Basis | None:
-        """L3 yaml changed → skip L2; keep L3 on touched platforms."""
-        platforms = buckets.l3_platforms()
-        if not platforms:
-            return None
-        return cls(enable_l3_platforms=platforms)
-
-
-@dataclass(frozen=True)
-class CiDecision:
-    """Final CI skip decision for one diff."""
-
-    skip_all: bool = False
-    skip_l2_l3: bool = False
-    device: CiDevice = field(default_factory=CiDevice)
-    message: str = ""
-
-    @classmethod
-    def skip_all_basis(cls, buckets: DiffBuckets, *, diff_range: str | None) -> bool:
-        """Docs / pytest skip-mark only → suppress entire default CI."""
-        if buckets.has_other_changes:
-            return False
-        if (buckets.has_l23_yaml_changes or buckets.has_l45_yaml_changes) and (
-            buckets.has_doc_changes or buckets.has_skip_test_changes
-        ):
-            return False
-        if not buckets.has_doc_changes and not buckets.has_skip_test_changes:
-            return False
-        if diff_range is None and not buckets.has_doc_changes:
-            return False
-        return True
-
-    @classmethod
-    def from_yaml_basis(
-        cls,
-        l2_l3_basis: SkipL2L3Basis | None,
-        l3_basis: SkipL3Basis | None,
-        l2_basis: SkipL2Basis | None,
-    ) -> CiDecision:
-        """Build a yaml-gated decision by merging L2/L3 skip bases.
-
-        Bases are applied as a union of enables: L2 yaml keeps L2 on touched
-        platforms, L3 yaml keeps L3 on touched platforms. Cross-platform mixes
-        (e.g. CUDA ready + AMD merge) must preserve both enables. The resulting
-        per-platform / per-level matrix is stored on ``device`` as ``skip_*``.
-        """
-        run = {platform: {"l2": True, "l3": True} for platform in PLATFORMS}
-
-        if l2_l3_basis is not None:
-            if l2_l3_basis.skip_all_l2:
-                for platform in PLATFORMS:
-                    run[platform]["l2"] = False
-            if l2_l3_basis.skip_all_l3:
-                for platform in PLATFORMS:
-                    run[platform]["l3"] = False
-
-        if l3_basis is not None:
-            for platform in PLATFORMS:
-                run[platform]["l3"] = False
-                run[platform]["l2"] = platform in l3_basis.enable_l2_platforms
-
-        if l2_basis is not None:
-            for platform in PLATFORMS:
-                if platform in l2_basis.enable_l3_platforms:
-                    run[platform]["l3"] = True
-                    if l3_basis is None or platform not in l3_basis.enable_l2_platforms:
-                        run[platform]["l2"] = False
-                elif l3_basis is None:
-                    # L3-yaml-only: disable platforms that did not change L3.
-                    run[platform]["l2"] = False
-                    run[platform]["l3"] = False
-                # else: leave L2 enables from SkipL3Basis; keep this platform's L3 off.
-
-        return cls(
-            skip_l2_l3=True,
-            device=cls._device_from_run(run),
-        )
-
-    @staticmethod
-    def _device_from_run(run: dict[str, dict[str, bool]]) -> CiDevice:
-        return CiDevice(
-            **{f"skip_{platform}_{level}": not run[platform][level] for platform in PLATFORMS for level in ("l2", "l3")}
-        )
-
-    def is_run(self, platform: str, level: str) -> bool:
-        if self.skip_all:
-            return False
-        if not self.skip_l2_l3:
-            return True
-        if level not in L23_LEVELS:
-            return True
-        return not self.device.is_skip(platform, level)
-
-
-@dataclass(frozen=True)
-class CiContext:
-    """Skip-ci decision plus git diff inputs used to compute it."""
-
-    decision: CiDecision
-    changed_files: list[str] | None
-    diff_range: str | None
-
-
-def _log(message: str) -> None:
-    print(f"{LOG}: {message}", file=sys.stderr)
-
-
-def _git(*args: str) -> subprocess.CompletedProcess[str]:
-    return subprocess.run(
-        ["git", *args],
-        check=False,
-        capture_output=True,
-        text=True,
-    )
-
-
-# --- Diff helpers ---
-
-
-def _resolve_diff_range() -> str | None:
-    """Return a git diff range for PR or main builds, or None when unavailable."""
-    is_pr = os.environ.get("BUILDKITE_PULL_REQUEST", "false") != "false" and os.environ.get(
-        "BUILDKITE_PULL_REQUEST", ""
-    )
-    commit = os.environ.get("BUILDKITE_COMMIT", "")
-
-    if is_pr:
-        base_branch = os.environ.get("BUILDKITE_PULL_REQUEST_BASE_BRANCH", "main")
-        base_ref = f"origin/{base_branch}"
-        if _git("rev-parse", "--verify", base_ref).returncode != 0:
-            _log(f"origin/{base_branch} not found locally; trying fetch")
-            _git("fetch", "--depth=200", "origin", base_branch)
-        if _git("rev-parse", "--verify", base_ref).returncode != 0:
-            if _git("rev-parse", "--verify", base_branch).returncode == 0:
-                base_ref = base_branch
-            else:
-                _log(f"cannot resolve PR base {base_branch}; using safe defaults")
-                return None
-        return f"{base_ref}...{commit}"
-
-    if os.environ.get("BUILDKITE_BRANCH", "") == "main":
-        if _git("rev-parse", "--verify", f"{commit}^").returncode != 0:
-            _log("main commit has no parent; using safe defaults")
-            return None
-        return f"{commit}^..{commit}"
-
-    _log("not PR/main build; using safe defaults")
-    return None
-
-
-def _changed_files_for_diff_range(diff_range: str | None) -> list[str] | None:
-    """Return changed file paths for *diff_range*, or None when unavailable."""
-    if diff_range is None:
-        return None
-
-    result = _git("diff", "--name-only", diff_range)
-    if result.returncode != 0:
-        _log(f"git diff failed ({diff_range}); using safe defaults")
-        return None
-
-    files = [line for line in result.stdout.splitlines() if line.strip()]
-    _log(f"{len(files)} changed file(s)")
-    return files
-
-
-def resolve_ci_context_from_git() -> CiContext:
-    """Resolve git diff once and return skip-ci decision plus changed files."""
-    diff_range = _resolve_diff_range()
-    changed_files = _changed_files_for_diff_range(diff_range)
-    decision = resolve_ci_decision(changed_files, diff_range=diff_range)
-    return CiContext(decision=decision, changed_files=changed_files, diff_range=diff_range)
-
-
-# --- Doc / skip-mark helpers ---
-
-
-_SKIP_MARK_RE = re.compile(r"pytest\.mark\.skip(?:if)?\b|pytest\.skip\s*\(")
-_PYTESTMARK_SKIP_RE = re.compile(r"pytest\.mark\.skip\b")
-_PYTEST_MARK_ONLY_RE = re.compile(r"pytest\.mark\.\w+")
-
-
-def _diff_only_contains_skip_mark_changes(diff_text: str) -> bool:
-    """Return True when a unified diff only *adds* pytest skip marks.
-
-    Deleting a skip mark re-enables the test and must not suppress CI. Editing an
-    existing skip (``-`` old / ``+`` new) still qualifies when at least one skip
-    mark is added.
-    """
-
-    def paren_balance(line: str) -> int:
-        return line.count("(") - line.count(")")
-
-    def is_blank_or_comment(line: str) -> bool:
-        stripped = line.strip()
-        return not stripped or stripped.startswith("#")
-
-    def is_skip_mark_line(line: str) -> bool:
-        return _SKIP_MARK_RE.search(line.strip()) is not None
-
-    def is_pytestmark_adjacent_line(line: str) -> bool:
-        stripped = line.strip().rstrip(",")
-        if not stripped or stripped in {"[", "]"} or stripped.startswith("#"):
-            return True
-        if stripped.startswith("pytestmark"):
-            return True
-        return _PYTEST_MARK_ONLY_RE.search(stripped) is not None
-
-    pending_depth = 0
-    saw_change = False
-    has_added_skip_mark = False
-    for raw_line in diff_text.splitlines():
-        if raw_line.startswith("@@"):
-            pending_depth = 0
-            continue
-        if not (raw_line.startswith("+") or raw_line.startswith("-")):
-            continue
-        if raw_line.startswith("+++") or raw_line.startswith("---"):
-            continue
-
-        saw_change = True
-        is_add = raw_line.startswith("+")
-        content = raw_line[1:]
-
-        if pending_depth > 0:
-            pending_depth += paren_balance(content)
-            if pending_depth < 0:
-                pending_depth = 0
-            continue
-
-        if is_blank_or_comment(content):
-            continue
-
-        if is_skip_mark_line(content):
-            if is_add:
-                has_added_skip_mark = True
-            pending_depth = max(0, paren_balance(content))
-            continue
-
-        if is_pytestmark_adjacent_line(content):
-            continue
-
-        return False
-
-    return saw_change and has_added_skip_mark
-
-
-def _is_skip_testcase_change(file_path: str, *, diff_range: str) -> bool:
-    """Return True when a test file diff is skip-mark-only (including new-file cases)."""
-    diff_result = _git("diff", diff_range, "--", file_path)
-    if diff_result.returncode != 0:
-        _log(f"skip-mark-only: git diff failed for {file_path}")
-        return False
-
-    diff_text = diff_result.stdout
-    if not diff_text.strip():
-        _log(f"skip-mark-only: empty diff for {file_path}")
-        return False
-
-    if _diff_only_contains_skip_mark_changes(diff_text):
-        return True
-
-    if "new file mode" not in diff_text and "--- /dev/null" not in diff_text:
-        _log(f"skip-mark-only: non-skip changes in {file_path}")
-        return False
-
-    commit = os.environ.get("BUILDKITE_COMMIT", "")
-    if not commit:
-        return False
-
-    content_result = _git("show", f"{commit}:{file_path}")
-    if content_result.returncode != 0:
-        _log(f"skip-mark-only: cannot read {file_path} at {commit}")
-        return False
-
-    content = content_result.stdout
-    match = re.search(r"^pytestmark\s*=\s*\[(.*?)^\s*\]", content, re.MULTILINE | re.DOTALL)
-    if match is not None and _PYTESTMARK_SKIP_RE.search(match.group(1)) is not None:
-        _log(f"skip-mark-only: new test file with module-level pytest.mark.skip: {file_path}")
-        return True
-    if re.search(r"^pytestmark\s*=\s*pytest\.mark\.skip\b", content, re.MULTILINE):
-        _log(f"skip-mark-only: new test file with module-level pytest.mark.skip: {file_path}")
-        return True
-
-    _log(f"skip-mark-only: new test file without module-level pytest.mark.skip: {file_path}")
-    return False
-
-
-def _classify_changed_files_into_buckets(changed_files: list[str], *, diff_range: str | None) -> DiffBuckets:
-    """Classify each changed file path into a ``DiffBuckets`` category."""
-    buckets = DiffBuckets()
-    for file_path in changed_files:
-        if not file_path:
-            continue
-        if file_path.startswith("docs/") or file_path.endswith(".md") or file_path == "mkdocs.yml":
-            buckets.docs.append(file_path)
-            continue
-        path = Path(file_path)
-        if path.suffix == ".py" and path.parts and path.parts[0] == "tests":
-            if diff_range is not None and _is_skip_testcase_change(file_path, diff_range=diff_range):
-                buckets.skip_tests.append(file_path)
-            else:
-                buckets.other.append(file_path)
-            continue
-        if file_path in L2_YAML_FILES:
-            platform = L2_YAML_FILES[file_path]
-            buckets.l2[platform].append(file_path)
-        elif file_path in L3_YAML_FILES:
-            platform = L3_YAML_FILES[file_path]
-            buckets.l3[platform].append(file_path)
-        elif file_path in L45_YAML_FILES:
-            platform = L45_YAML_FILES[file_path]
-            buckets.l45[platform].append(file_path)
-        else:
-            buckets.other.append(file_path)
-    return buckets
-
-
-# --- Decision ---
-
-
-def _finish(decision: CiDecision, message: str) -> CiDecision:
-    finished = replace(decision, message=message)
-    _log(message)
-    return finished
-
-
-def _format_yaml_gated_message(buckets: DiffBuckets, decision: CiDecision) -> str:
-    """Human-readable summary of which CI YAML changed and which L2/L3 targets run."""
-    changed_parts: list[str] = []
-    for level_name, by_platform in (("L2", buckets.l2), ("L3", buckets.l3), ("L4/L5", buckets.l45)):
-        files = [path for platform in PLATFORMS for path in by_platform[platform]]
-        if files:
-            changed_parts.append(f"{level_name}=[{', '.join(files)}]")
-
-    run_targets = [
-        f"{platform}/{level}" for platform in PLATFORMS for level in ("l2", "l3") if decision.is_run(platform, level)
-    ]
-    skip_targets = [
-        f"{platform}/{level}"
-        for platform in PLATFORMS
-        for level in ("l2", "l3")
-        if not decision.is_run(platform, level)
-    ]
-
-    changed = "; ".join(changed_parts) if changed_parts else "none"
-    run = ", ".join(run_targets) if run_targets else "none"
-    skip = ", ".join(skip_targets) if skip_targets else "none"
-    if buckets.has_doc_changes or buckets.has_skip_test_changes:
-        return (
-            "CI config YAML + docs/skip-mark changed — follow CI YAML gating; "
-            f"changed: {changed}; run: {run}; skip: {skip}"
-        )
-    return f"only CI config YAML changed — changed: {changed}; run: {run}; skip: {skip}"
-
-
-def resolve_ci_decision(
-    changed_files: list[str] | None = None,
-    *,
-    diff_range: str | None = None,
-) -> CiDecision:
-    if changed_files is None:
-        return _finish(CiDecision(), "could not resolve changed files; run normal CI")
-
-    buckets = _classify_changed_files_into_buckets(changed_files, diff_range=diff_range)
-    if buckets.has_other_changes or not buckets.has_skip_ci_scope_changes:
-        return _finish(CiDecision(), "product or non-whitelisted changes present; run normal CI")
-
-    if CiDecision.skip_all_basis(buckets, diff_range=diff_range):
-        return _finish(
-            CiDecision(skip_all=True),
-            "CI skipped — docs or pytest skip-mark changes only",
-        )
-
-    # Docs / skip-mark mixed with whitelisted CI YAML → same yaml-gated path
-    # as CI-YAML-only (docs/skip-mark do not widen to normal CI).
-    if not buckets.has_l23_yaml_changes and not buckets.has_l45_yaml_changes:
-        if buckets.has_skip_test_changes and diff_range is None:
-            message = (
-                "only pytest skip-mark test changes detected, but no git diff range "
-                "is available to verify them (skip-all requires diff_range); run normal CI"
-            )
-        elif buckets.has_skip_test_changes:
-            message = "pytest skip-mark test changes did not qualify for skip-all and no ci yaml changed; run normal CI"
-        else:
-            message = "doc/skip-mark changes did not qualify for skip-all; run normal CI"
-        return _finish(CiDecision(), message)
-
-    decision = CiDecision.from_yaml_basis(
-        SkipL2L3Basis.from_buckets(buckets),
-        SkipL3Basis.from_buckets(buckets),
-        SkipL2Basis.from_buckets(buckets),
-    )
-    return _finish(decision, _format_yaml_gated_message(buckets, decision))
-
-
-def main() -> int:
-    parser = argparse.ArgumentParser(
-        description=__doc__,
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    subparsers = parser.add_subparsers(dest="command", required=True)
-
-    gate_parser = subparsers.add_parser(
-        "gate",
-        help="exit 0 when bootstrap should stop (skip-all or PLATFORM/LEVEL disabled); logs once",
-    )
-    gate_parser.add_argument("platform", help="cuda, amd, intel, or npu")
-    gate_parser.add_argument("level", choices=("l2", "l3"), help="test level")
-
-    subparsers.add_parser(
-        "check-skip-all",
-        help="exit 0 when docs/skip-mark-only diff should skip entire CI upload",
-    )
-
-    skip_parser = subparsers.add_parser(
-        "check-skip-l2-l3",
-        help="exit 0 when PLATFORM l2/l3 pipeline should be skipped (CI config YAML-only diffs)",
-    )
-    skip_parser.add_argument("platform", help="cuda, amd, intel, or npu")
-    skip_parser.add_argument("level", choices=("l2", "l3"), help="test level")
-
-    subparsers.add_parser(
-        "print-annotate",
-        help="print human-readable skip reason for Buildkite annotation",
-    )
-
-    args = parser.parse_args()
-    decision = resolve_ci_context_from_git().decision
-
-    if args.command == "gate":
-        if decision.skip_all:
-            print("skip-all")
-            return 0
-        if not decision.is_run(args.platform, args.level):
-            print("skip-l23")
-            return 0
-        return 1
-
-    if args.command == "check-skip-all":
-        return 0 if decision.skip_all else 1
-
-    if args.command == "check-skip-l2-l3":
-        return 0 if not decision.is_run(args.platform, args.level) else 1
-
-    if args.command == "print-annotate":
-        print(decision.message or "CI will run normally")
-        return 0
-
-    return 1
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())

.buildkite/common/scripts/upload_pipeline.py

@@ -1,449 +0,0 @@
-#!/usr/bin/env python3
-# SPDX-License-Identifier: Apache-2.0
-"""Render and optionally upload Buildkite pipeline YAML with diff-aware logic.
-
-Bootstrap mode (``bootstrap-upload-steps.yml``):
-  - Hook uploads the entry YAML (``pipeline.yml`` / ``pipeline-npu.yml``) with one step that runs
-    ``upload_pipeline.py --upload <platform>/bootstrap-upload-steps.yml``.
-  - Injects ``if`` by step ``key`` from skip-ci and uploads child steps (image build, L2–L5 upload).
-  - Detect docs-only, pytest skip-mark-only, or combined skip-ci from git diff.
-  - When only CI level YAML changes, enable **L2/L3** upload steps for affected levels only.
-
-Test pipeline mode (e.g. test-merge.yml):
-  - Drop steps whose ``source_file_dependencies`` do not match changed files.
-  - Expand uploader-only ``mirror_hardwares: l4_1`` into ``agents`` (+ optional ``image``
-    for NPU) + ``plugins`` (see ci_mirror_hardwares.yml).
-
-Usage:
-  python3 upload_pipeline.py [--upload] [--all | --e2e] <pipeline.yml>
-
-Requires PyYAML (``pip install pyyaml``); installs it automatically when missing.
-"""
-
-from __future__ import annotations
-
-import argparse
-import copy
-import subprocess
-import sys
-from functools import lru_cache
-from pathlib import Path
-from typing import Any
-
-try:
-    import yaml
-except ModuleNotFoundError:
-    subprocess.run(
-        [sys.executable, "-m", "pip", "install", "-q", "pyyaml"],
-        check=True,
-    )
-    import yaml
-
-from skip_ci import (
-    ROOT,
-    resolve_ci_context_from_git,
-)
-
-# --- Constants ---
-
-LOG = "upload_pipeline"
-BOOTSTRAP_STEPS_FILENAME = "bootstrap-upload-steps.yml"
-BOOTSTRAP_IMAGE_BUILD_KEYS = frozenset({"image-build", "image-build-a2", "image-build-a3"})
-BOOTSTRAP_UPLOAD_IF_KEYS = {
-    "upload-ready-pipeline": "ready",
-    "upload-merge-pipeline": "merge",
-    "upload-nightly-pipeline": "nightly",
-    "upload-weekly-pipeline": "weekly",
-}
-E2E_GROUP_MARKER = "E2E Test"
-CI_MIRROR_HARDWARES_PATH = ROOT / ".buildkite/common/ci_mirror_hardwares.yml"
-
-CUDA_NIGHTLY_ONLY = (
-    '(build.pull_request.labels includes "nightly-test") || (build.branch == "main" && build.env("NIGHTLY") == "1")'
-)
-NPU_NIGHTLY_ONLY = (
-    '(build.branch == "main" && build.env("NIGHTLY") == "1") || '
-    '(build.branch != "main" && ('
-    'build.pull_request.labels includes "nightly-test" || '
-    'build.pull_request.labels includes "omni-test" || '
-    'build.pull_request.labels includes "tts-test" || '
-    'build.pull_request.labels includes "diffusion-x2iat-test" || '
-    'build.pull_request.labels includes "diffusion-x2v-test"'
-    "))"
-)
-
-
-# --- Logging ---
-
-
-def _log(message: str) -> None:
-    print(f"{LOG}: {message}", file=sys.stderr)
-
-
-# --- Bootstrap pipeline (bootstrap-upload-steps.yml) ---
-
-
-def _get_bootstrap_platform(path: Path) -> str:
-    parts = path.as_posix().split("/")
-    return "npu" if "npu" in parts else "cuda"
-
-
-def _load_bootstrap_steps(path: Path) -> str:
-    if path.name != BOOTSTRAP_STEPS_FILENAME:
-        raise ValueError(f"expected {BOOTSTRAP_STEPS_FILENAME}, got {path.name}")
-    return path.read_text(encoding="utf-8")
-
-
-def _format_bootstrap_if(expr: str) -> str:
-    """Return a Buildkite ``if`` string. Buildkite rejects YAML bool ``if`` values."""
-    if expr in ("true", "false"):
-        return expr
-    return f"({expr})"
-
-
-def _compute_bootstrap_if_exprs(*, decision, platform: str) -> dict[str, str]:
-    disabled = "false"
-    nightly_main = 'build.branch == "main" && build.env("NIGHTLY") == "1"'
-    nightly_only = NPU_NIGHTLY_ONLY if platform == "npu" else CUDA_NIGHTLY_ONLY
-
-    if platform == "npu":
-        ready_pr = (
-            'build.branch != "main" && ('
-            'build.pull_request.labels includes "npu-test" || '
-            'build.pull_request.labels includes "ready"'
-            ")"
-        )
-        nightly_label_if = nightly_only
-        weekly_label_if = disabled
-        merge_base = disabled
-    else:
-        ready_pr = 'build.branch != "main" && build.pull_request.labels includes "ready"'
-        merge_main = 'build.branch == "main" && build.env("NIGHTLY") != "1" && build.env("WEEKLY") != "1"'
-        merge_pr = 'build.branch != "main" && build.pull_request.labels includes "merge-test"'
-        nightly_label_if = (
-            '(build.branch == "main" && build.env("NIGHTLY") == "1") || '
-            '(build.branch != "main" && ('
-            'build.pull_request.labels includes "nightly-test" || '
-            'build.pull_request.labels includes "omni-test" || '
-            'build.pull_request.labels includes "tts-test" || '
-            'build.pull_request.labels includes "diffusion-x2iat-test" || '
-            'build.pull_request.labels includes "diffusion-x2v-test"'
-            "))"
-        )
-        weekly_label_if = (
-            '(build.branch == "main" && build.env("WEEKLY") == "1") || '
-            '(build.branch != "main" && build.pull_request.labels includes "weekly-test")'
-        )
-        merge_base = f"({nightly_main}) || (({merge_main}) || ({merge_pr}))"
-
-    ready_base = f"({nightly_main}) || ({ready_pr})"
-    weekly_main = 'build.branch == "main" && build.env("WEEKLY") == "1"'
-
-    if decision.skip_all:
-        # Docs / skip-mark only: no PR-label escape hatch. Main scheduled
-        # NIGHTLY=1 still runs L4 + L2/L3 (--e2e); WEEKLY=1 still runs L5.
-        image_expr = f"({nightly_main}) || ({weekly_main})" if platform == "cuda" else nightly_main
-        ready_expr = nightly_main
-        merge_expr = nightly_main if platform == "cuda" else disabled
-        nightly_expr = nightly_main
-        weekly_expr = weekly_main if platform == "cuda" else disabled
-    elif decision.skip_l2_l3:
-        l2_enabled = decision.is_run("npu", "l2") if platform == "npu" else decision.is_run("cuda", "l2")
-        l3_enabled = platform == "cuda" and decision.is_run("cuda", "l3")
-
-        ready_expr = ready_base if l2_enabled else disabled
-        merge_expr = merge_base if l3_enabled else disabled
-        nightly_expr = nightly_label_if
-        weekly_expr = weekly_label_if if platform == "cuda" else disabled
-
-        image_parts = [f"({nightly_label_if})"]
-        if platform == "cuda":
-            image_parts.append(f"({weekly_label_if})")
-        if l2_enabled:
-            image_parts.insert(0, f"({ready_base})")
-        if l3_enabled:
-            image_parts.insert(1 if l2_enabled else 0, f"({merge_base})")
-        image_expr = " || ".join(image_parts)
-    else:
-        image_expr = "true"
-        ready_expr = ready_base
-        merge_expr = merge_base if platform == "cuda" else disabled
-        nightly_expr = nightly_label_if
-        weekly_expr = weekly_label_if if platform == "cuda" else disabled
-
-    return {
-        "image": _format_bootstrap_if(image_expr),
-        "ready": _format_bootstrap_if(ready_expr),
-        "merge": _format_bootstrap_if(merge_expr),
-        "nightly": _format_bootstrap_if(nightly_expr),
-        "weekly": _format_bootstrap_if(weekly_expr),
-    }
-
-
-def _apply_bootstrap_if(steps: list[Any], if_exprs: dict[str, str]) -> list[Any]:
-    """Inject ``if`` by step key; drop steps that are unconditionally disabled."""
-    kept: list[Any] = []
-    for step in steps:
-        if not isinstance(step, dict):
-            kept.append(step)
-            continue
-        nested = step.get("steps")
-        if isinstance(nested, list):
-            nested_kept = _apply_bootstrap_if(nested, if_exprs)
-            if nested_kept:
-                kept.append({**step, "steps": nested_kept})
-            continue
-        key = step.get("key")
-        if key in BOOTSTRAP_IMAGE_BUILD_KEYS:
-            step["if"] = if_exprs["image"]
-        elif key in BOOTSTRAP_UPLOAD_IF_KEYS:
-            step["if"] = if_exprs[BOOTSTRAP_UPLOAD_IF_KEYS[key]]
-        if_expr = step.get("if")
-        if if_expr == "false":
-            _log(f"omit disabled bootstrap step {key!r}")
-            continue
-        if if_expr == "true":
-            # Unconditional step: omit ``if`` (Buildkite requires string ``if``, not YAML bool).
-            step.pop("if", None)
-        kept.append(step)
-    return kept
-
-
-def _render_bootstrap_pipeline(
-    steps_yaml: str,
-    *,
-    decision,
-    path: Path,
-) -> str:
-    """Load bootstrap steps YAML and inject ``if`` expressions from skip-ci decision."""
-    doc = yaml.safe_load(steps_yaml)
-    if not isinstance(doc, dict):
-        raise ValueError(f"invalid bootstrap steps YAML for {path}")
-    steps = doc.get("steps")
-    if not isinstance(steps, list):
-        raise ValueError(f"bootstrap steps YAML must contain steps: list in {path}")
-
-    platform = _get_bootstrap_platform(path)
-    if_exprs = _compute_bootstrap_if_exprs(decision=decision, platform=platform)
-    doc["steps"] = _apply_bootstrap_if(steps, if_exprs)
-    return yaml.safe_dump(doc, sort_keys=False)
-
-
-# --- Test pipeline (test-ready.yml, test-merge.yml) ---
-
-
-@lru_cache(maxsize=1)
-def _load_mirror_hardwares() -> dict[str, dict[str, Any]]:
-    if not CI_MIRROR_HARDWARES_PATH.is_file():
-        raise FileNotFoundError(f"missing CI mirror_hardwares registry: {CI_MIRROR_HARDWARES_PATH}")
-    doc = yaml.safe_load(CI_MIRROR_HARDWARES_PATH.read_text(encoding="utf-8"))
-    if not isinstance(doc, dict):
-        raise ValueError(f"invalid CI mirror_hardwares registry: {CI_MIRROR_HARDWARES_PATH}")
-    presets = doc.get("mirror_hardwares")
-    if not isinstance(presets, dict):
-        raise ValueError(f"mirror_hardwares must be a mapping in {CI_MIRROR_HARDWARES_PATH}")
-    return presets
-
-
-def _expand_mirror_hardwares(step: dict[str, Any]) -> dict[str, Any]:
-    """Replace uploader-only ``mirror_hardwares`` with preset fields from ci_mirror_hardwares.yml."""
-    hardware = step.get("mirror_hardwares")
-    if hardware is None:
-        return step
-
-    if not isinstance(hardware, str) or not hardware.strip():
-        raise ValueError(
-            f"mirror_hardwares must be a non-empty string in step {_get_step_label(step)!r}",
-        )
-
-    preset = _load_mirror_hardwares().get(hardware)
-    if preset is None:
-        known = ", ".join(sorted(_load_mirror_hardwares()))
-        raise ValueError(
-            f"unknown mirror_hardwares {hardware!r} in step {_get_step_label(step)!r}; known: {known}",
-        )
-
-    if step.get("agents") is not None or step.get("plugins") is not None or step.get("image") is not None:
-        raise ValueError(
-            f"step {_get_step_label(step)!r} sets mirror_hardwares together with agents/plugins/image; "
-            "use mirror_hardwares only",
-        )
-
-    expanded = copy.deepcopy(preset)
-    return {key: value for key, value in step.items() if key != "mirror_hardwares"} | expanded
-
-
-def _match_source_file(changed_files: list[str], prefixes: list[str]) -> bool:
-    for path in changed_files:
-        for prefix in prefixes:
-            normalized = prefix.rstrip("/")
-            if path == normalized or path.startswith(f"{normalized}/"):
-                return True
-    return False
-
-
-def _get_step_label(step: dict[str, Any]) -> str:
-    return str(step.get("group") or step.get("label") or "<step>")
-
-
-def _process_test_steps(
-    steps: list[Any],
-    changed_files: list[str] | None,
-) -> list[Any]:
-    """Drop steps by ``source_file_dependencies`` when *changed_files* is set; always strip that field."""
-    processed: list[Any] = []
-    for step in steps:
-        if not isinstance(step, dict):
-            processed.append(step)
-            continue
-
-        deps = step.get("source_file_dependencies")
-        if deps is not None and not isinstance(deps, list):
-            raise ValueError(
-                f"source_file_dependencies must be a list in step {_get_step_label(step)!r}",
-            )
-        if changed_files is not None and deps is not None and not _match_source_file(changed_files, deps):
-            _log(f"skip {_get_step_label(step)!r} (no changes under {deps})")
-            continue
-
-        nested = step.get("steps")
-        if nested is not None:
-            kept_nested = _process_test_steps(nested, changed_files)
-            if changed_files is not None and not kept_nested:
-                _log(f"omit empty group {_get_step_label(step)!r}")
-                continue
-            new_step = {key: value for key, value in step.items() if key != "source_file_dependencies"}
-            new_step["steps"] = kept_nested
-            processed.append(new_step)
-            continue
-
-        if deps is not None:
-            processed.append(
-                _expand_mirror_hardwares(
-                    {key: value for key, value in step.items() if key != "source_file_dependencies"},
-                ),
-            )
-        else:
-            processed.append(_expand_mirror_hardwares(step))
-
-    return processed
-
-
-def _select_e2e_group_steps(steps: list[Any]) -> list[Any]:
-    """Keep only top-level groups whose name contains ``E2E_GROUP_MARKER``."""
-    selected = [
-        step
-        for step in steps
-        if isinstance(step, dict) and isinstance(step.get("group"), str) and E2E_GROUP_MARKER in step["group"]
-    ]
-    if not selected:
-        _log(f"no group matching {E2E_GROUP_MARKER!r} found")
-    else:
-        _log(f"keep {len(selected)} group(s) matching {E2E_GROUP_MARKER!r}")
-    return selected
-
-
-def _render_test_pipeline(
-    doc: dict[str, Any],
-    changed_files: list[str] | None,
-    *,
-    e2e_only: bool = False,
-) -> dict[str, Any]:
-    """Filter steps by PR diff and strip uploader-only ``source_file_dependencies`` metadata."""
-    steps = doc.get("steps")
-    if not isinstance(steps, list):
-        return doc
-    if e2e_only:
-        steps = _select_e2e_group_steps(steps)
-    steps = _process_test_steps(steps, changed_files)
-    return {**doc, "steps": steps}
-
-
-# --- Entry (read file → bootstrap or test render → YAML string) ---
-
-
-def _render_pipeline(
-    path: Path,
-    *,
-    force_all: bool = False,
-    e2e_only: bool = False,
-) -> str:
-    if path.name == BOOTSTRAP_STEPS_FILENAME:
-        ctx = resolve_ci_context_from_git()
-        continuation = _load_bootstrap_steps(path)
-        return _render_bootstrap_pipeline(
-            continuation,
-            decision=ctx.decision,
-            path=path,
-        )
-
-    text = path.read_text(encoding="utf-8")
-    ctx = resolve_ci_context_from_git()
-    if force_all or e2e_only:
-        changed_files = None
-    else:
-        changed_files = ctx.changed_files
-
-    doc = yaml.safe_load(text)
-    if not isinstance(doc, dict):
-        raise ValueError(f"invalid pipeline YAML: {path}")
-
-    doc = _render_test_pipeline(doc, changed_files, e2e_only=e2e_only)
-    return yaml.safe_dump(doc, sort_keys=False)
-
-
-def _upload_to_buildkite(content: str) -> None:
-    subprocess.run(
-        ["buildkite-agent", "pipeline", "upload"],
-        input=content,
-        text=True,
-        check=True,
-    )
-
-
-# --- CLI ---
-
-
-def main() -> int:
-    parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument(
-        "pipeline",
-        nargs="?",
-        default=".buildkite/cuda/bootstrap-upload-steps.yml",
-        help="Pipeline YAML path (default: .buildkite/cuda/bootstrap-upload-steps.yml)",
-    )
-    parser.add_argument(
-        "--upload",
-        action="store_true",
-        help="Pipe rendered YAML to buildkite-agent pipeline upload",
-    )
-    mode = parser.add_mutually_exclusive_group()
-    mode.add_argument(
-        "--all",
-        action="store_true",
-        help="Keep all steps (disable diff-aware skipping)",
-    )
-    mode.add_argument(
-        "--e2e",
-        action="store_true",
-        help="Keep only the E2E Test group",
-    )
-    args = parser.parse_args()
-
-    path = Path(args.pipeline)
-    if not path.is_absolute():
-        path = ROOT / path
-    if not path.is_file():
-        _log(f"missing pipeline file: {path}")
-        return 1
-
-    rendered = _render_pipeline(path, force_all=args.all, e2e_only=args.e2e)
-    if args.upload:
-        _upload_to_buildkite(rendered)
-    else:
-        sys.stdout.write(rendered)
-    return 0
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())

.buildkite/cuda/bootstrap-upload-steps.yml

@@ -1,55 +0,0 @@
-# Uploaded by upload_pipeline.py --upload (not the Buildkite hook).
-# ``if`` is injected by step ``key`` from skip-ci at upload time.
-steps:
-  - label: ":docker: Build image"
-    key: image-build
-    commands:
-      - "bash .buildkite/cuda/scripts/build-ci-image.sh"
-    agents:
-      queue: "cpu_queue_premerge"
-
-  # L2 Test — PR ready label (diff-aware) or main+NIGHTLY=1 (--e2e, full E2E group)
-  - label: "Upload Ready Pipeline"
-    depends_on: image-build
-    key: upload-ready-pipeline
-    commands:
-      - |
-        EXTRA=""
-        if [ "${NIGHTLY:-}" = "1" ] && [ "${BUILDKITE_BRANCH}" = "main" ]; then
-          EXTRA="--e2e"
-        fi
-        python3 .buildkite/common/scripts/upload_pipeline.py --upload $$EXTRA .buildkite/cuda/test-ready.yml
-    agents:
-      queue: "cpu_queue_premerge"
-
-  # L3 Test — PR merge-test label (diff-aware) or main+NIGHTLY=1 (--e2e, full E2E group)
-  - label: "Upload Merge Pipeline"
-    depends_on: image-build
-    key: upload-merge-pipeline
-    commands:
-      - |
-        EXTRA=""
-        if [ "${NIGHTLY:-}" = "1" ] && [ "${BUILDKITE_BRANCH}" = "main" ]; then
-          EXTRA="--e2e"
-        fi
-        python3 .buildkite/common/scripts/upload_pipeline.py --upload $$EXTRA .buildkite/cuda/test-merge.yml
-    agents:
-      queue: "cpu_queue_premerge"
-
-  # L4 Test — main+NIGHTLY=1 (scheduled), or PR with specific label (e.g. add label then Rebuild)
-  - label: "Upload Nightly Pipeline"
-    depends_on: image-build
-    key: upload-nightly-pipeline
-    commands:
-      - python3 .buildkite/common/scripts/upload_pipeline.py --upload .buildkite/cuda/test-nightly.yml
-    agents:
-      queue: "cpu_queue_premerge"
-
-  # L5 Test — main+WEEKLY=1 (scheduled), or PR with weekly-test label
-  - label: "Upload Weekly Pipeline"
-    depends_on: image-build
-    key: upload-weekly-pipeline
-    commands:
-      - python3 .buildkite/common/scripts/upload_pipeline.py --upload .buildkite/cuda/test-weekly.yml
-    agents:
-      queue: "cpu_queue_premerge"

.buildkite/cuda/pipeline.yml

@@ -1,9 +0,0 @@
-# Hook uploads this entry YAML; upload_pipeline.py --upload reads bootstrap-upload-steps.yml
-# and injects ``if`` by step ``key`` from skip-ci.
-steps:
-  - label: ":github: Resolve skip-ci & upload pipeline"
-    key: upload-ci-pipeline
-    commands:
-      - "python3 .buildkite/common/scripts/upload_pipeline.py --upload .buildkite/cuda/bootstrap-upload-steps.yml"
-    agents:
-      queue: "cpu_queue_premerge"

.buildkite/cuda/scripts/build-ci-image.sh

@@ -1,52 +0,0 @@
-#!/bin/bash
-set -euo pipefail
-
-# Build and push the CI Docker image with registry-based layer caching.
-#
-# Usage: build-ci-image.sh
-#
-# Expects the following environment variables (set by Buildkite):
-#   BUILDKITE_COMMIT          - commit SHA used as the image tag
-ECR_NAMESPACE="public.ecr.aws/q9t5s3a7"
-REGISTRY="${ECR_NAMESPACE}/vllm-ci-test-repo"
-REGION="us-east-1"
-DOCKERFILE="docker/Dockerfile.ci"
-BUILDER_NAME="vllm-omni-builder"
-
-# Ensure that the env vars are actually set, otherwise exit early
-if [ -z "${BUILDKITE_COMMIT:-}" ]; then
-    echo "ERROR: BUILDKITE_COMMIT is not set"
-    exit 1
-fi
-echo "BUILDKITE_COMMIT: ${BUILDKITE_COMMIT}"
-
-# Authenticate to ECR Public
-aws ecr-public get-login-password --region "$REGION" \
-    | docker login --username AWS --password-stdin "$ECR_NAMESPACE"
-
-# Compute the cache tag for the dependencies image as the hash of the contents.
-# This is because dependencies don't change often, so most PRs will have the same hash.
-#
-# The Dockerfile is also included to avoid churn in the cached image based on the vLLM version.
-DEP_FILES="pyproject.toml setup.py requirements/*.txt docker/Dockerfile.ci"
-CACHE_KEY=$(cat ${DEP_FILES} | sha256sum | cut -c1-16)
-CACHE_TAG="deps-cache-${CACHE_KEY}"
-echo "Cache key: ${CACHE_TAG}"
-
-# Set up buildx with docker-container driver; we need to do this
-# since cache export is not supported for the default docker driver
-# that is running in the CI.
-docker buildx inspect $BUILDER_NAME >/dev/null 2>&1 \
-|| docker buildx create --name $BUILDER_NAME --driver docker-container
-docker buildx use $BUILDER_NAME
-
-echo "Building image tag: ${REGISTRY}:${BUILDKITE_COMMIT}"
-
-# Build + push the image to the registry, using the hash from the dependencies.
-# Note that the caching here is layerwise, so we're just making sure we always
-# can cache hit on everything but the last copy at the moment.
-docker buildx build --push --progress=plain \
-    --cache-from "type=registry,ref=${REGISTRY}:${CACHE_TAG}" \
-    --cache-to "type=registry,ref=${REGISTRY}:${CACHE_TAG},mode=max,compression=zstd" \
-    --file "$DOCKERFILE" \
-    -t "${REGISTRY}:${BUILDKITE_COMMIT}" .

.buildkite/cuda/test-merge.yml

@@ -1,264 +0,0 @@
-env:
-  VLLM_WORKER_MULTIPROC_METHOD: spawn
-  VLLM_USE_FLASHINFER_MOE_FP16: 0
-  HF_HUB_DOWNLOAD_TIMEOUT: 300
-  HF_HUB_ETAG_TIMEOUT: 60
-
-steps:
-  - group: ":card_index_dividers: Simple Test"
-    depends_on: upload-merge-pipeline
-    steps:
-      - label: "Simple · Model Executor Test"
-        commands:
-          - "timeout 20m pytest -sv tests/model_executor -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-        mirror_hardwares: l4_1
-
-      - label: "Simple · Diffusion Test"
-        commands:
-          - "timeout 20m pytest -sv tests/diffusion -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-        mirror_hardwares: l4_1
-
-      - label: "Simple · Engine&Entrypoints Test"
-        commands:
-          - "timeout 20m pytest -sv tests/entrypoints tests/engine -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-        mirror_hardwares: l4_1
-
-      - label: "Simple · Other Test"
-        commands:
-          - "timeout 20m pytest -sv tests/ -m 'core_model and cpu' --ignore=tests/diffusion --ignore=tests/model_executor --ignore=tests/entrypoints --ignore=tests/engine --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-        mirror_hardwares: l4_1
-
-  - group: ":card_index_dividers: Diffusion Test"
-    depends_on: upload-merge-pipeline
-    steps:
-      - label: "Diffusion · LoRA Test"
-        timeout_in_minutes: 30
-        commands:
-          - pytest -sv tests/diffusion/lora/ -m 'advanced_model and cuda' --run-level "advanced_model"
-        mirror_hardwares: l4_1
-
-  - label: "Distributed Test"
-    depends_on: upload-merge-pipeline
-    timeout_in_minutes: 60
-    commands:
-      - |
-        timeout 55m bash -c "
-          set -e
-          export VLLM_IMAGE_FETCH_TIMEOUT=60
-          pytest -s -v tests/distributed -m 'advanced_model and cuda and H100' --run-level 'advanced_model'
-        "
-    mirror_hardwares: h100_1
-
-  - group: ":card_index_dividers: Entrypoints Test"
-    depends_on: upload-merge-pipeline
-    steps:
-      - label: "Entrypoint Test with H100"
-        # TEMPORARY 60 -> 90: engine startup/sleep-wake is ~13-15 min slower per
-        # run on the vLLM 0.26 image (model loading ~2x, init ~2x; see builds
-        # 2915 vs 2916), which pushed this suite past 60 min. Revert once the
-        # 0.26 startup regression is understood and fixed.
-        timeout_in_minutes: 90
-        commands:
-          - pytest -s -v tests/entrypoints/ -m "advanced_model and cuda and H100" --run-level "advanced_model"
-        mirror_hardwares: h100_2
-
-      - label: "Entrypoint Test with L4"
-        timeout_in_minutes: 60
-        commands:
-          - pytest -s -v tests/entrypoints/ -m "advanced_model and cuda and L4" --run-level "advanced_model"
-        mirror_hardwares: l4_1
-
-  - group: ":card_index_dividers: E2E Test"
-    depends_on: upload-merge-pipeline
-    steps:
-      - label: "TTS · Qwen3-TTS CustomVoice Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen3_tts_customvoice.py
-          - tests/e2e/offline_inference/test_qwen3_tts_customvoice.py
-          - vllm_omni/model_executor/models/qwen3_tts/
-          - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
-          - vllm_omni/deploy/qwen3_tts.yaml
-        commands:
-          - |
-            timeout 40m bash -c "
-              export VLLM_LOGGING_LEVEL=DEBUG
-              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
-              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py tests/e2e/offline_inference/test_qwen3_tts_customvoice.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-            "
-        mirror_hardwares: l4_1
-
-      - label: "TTS · Qwen3-TTS Base Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen3_tts_base.py
-          - tests/e2e/offline_inference/test_qwen3_tts_base.py
-          - vllm_omni/model_executor/models/qwen3_tts/
-          - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
-          - vllm_omni/deploy/qwen3_tts.yaml
-        commands:
-          - |
-            timeout 40m bash -c "
-              export VLLM_LOGGING_LEVEL=DEBUG
-              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
-              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py tests/e2e/offline_inference/test_qwen3_tts_base.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-            "
-        mirror_hardwares: l4_1
-
-      - label: "TTS · Higgs-Audio-V3 Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_higgs_audio_v3.py
-          - vllm_omni/model_executor/models/higgs_audio_v3/
-          - vllm_omni/model_executor/stage_input_processors/higgs_audio_v3.py
-          - vllm_omni/deploy/higgs_multimodal_qwen3.yaml
-        commands:
-          - |
-            timeout 20m bash -c "
-              export VLLM_WORKER_MULTIPROC_METHOD=spawn
-              export VLLM_USE_DEEP_GEMM=0
-              export VLLM_MOE_USE_DEEP_GEMM=0
-              pytest -s -v tests/e2e/online_serving/test_higgs_audio_v3.py -m 'advanced_model' --run-level 'advanced_model'
-            "
-        mirror_hardwares: l4_1
-
-      - label: "Omni · Qwen3-Omni Test"
-        source_file_dependencies:
-          - tests/e2e/offline_inference/test_qwen3_omni.py
-          - tests/e2e/online_serving/test_qwen3_omni.py
-          - vllm_omni/model_executor/models/qwen3_omni/
-          - vllm_omni/model_executor/stage_input_processors/qwen3_omni.py
-          - vllm_omni/deploy/qwen3_omni_moe.yaml
-        timeout_in_minutes: 50
-        commands:
-          - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-        mirror_hardwares: h100_2
-
-      - label: "Omni · MiniCPM-o 4.5 Test"
-        source_file_dependencies:
-          - tests/e2e/offline_inference/test_minicpmo_4_5.py
-          - tests/e2e/online_serving/test_minicpmo_4_5.py
-          - vllm_omni/deploy/minicpmo_4_5.yaml
-        timeout_in_minutes: 50
-        commands:
-          - pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-        # h100_2, not h100_1: advanced_model asserts transcribe every audio
-        # response with Whisper, and tests/helpers/media.py only uses an
-        # accelerator for Whisper when a spare GPU exists. On a single card it
-        # grades on CPU: ~8-10 min per clip vs ~30 s, which alone overruns the
-        # 50-minute job timeout (build 2956).
-        mirror_hardwares: h100_2
-
-      - label: "Omni · MiniCPM-o 4.5 Duplex Test"
-        source_file_dependencies:
-          - tests/assets/minicpmo_4_5/response_required_16k.wav
-          - tests/assets/minicpmo_4_5/soft_interrupt_16k.wav
-          - tests/e2e/online_serving/test_minicpmo_4_5_duplex.py
-          - tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
-          - tests/e2e/online_serving/test_minicpmo_realtime_duplex_drivers.py
-          - tests/e2e/online_serving/helpers/minicpmo_realtime_duplex_scenarios.py
-          - tests/e2e/online_serving/run_minicpmo_realtime_duplex_multi_session.py
-          - tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py
-          - tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py
-          - vllm_omni/deploy/minicpmo_4_5_duplex.yaml
-          - vllm_omni/experimental/fullduplex/
-          - vllm_omni/model_executor/models/minicpmo_4_5/
-          - vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
-          - vllm_omni/core/sched/
-          - vllm_omni/outputs/multimodal_accumulation.py
-          - vllm_omni/engine/stage_init_utils.py
-          - vllm_omni/engine/async_omni_engine.py
-          - vllm_omni/entrypoints/cli/serve.py
-        timeout_in_minutes: 50
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-        mirror_hardwares: h100_1
-
-      - label: "TTS · VoxCPM2 Test"
-        source_file_dependencies:
-          - tests/e2e/offline_inference/test_voxcpm2_tts.py
-          - tests/e2e/online_serving/test_voxcpm2_tts.py
-          - vllm_omni/model_executor/models/voxcpm2/
-          - vllm_omni/deploy/voxcpm2.yaml
-        timeout_in_minutes: 30
-        commands:
-          - |
-            timeout 30m bash -c "
-              export VLLM_LOGGING_LEVEL=DEBUG
-              export VLLM_WORKER_MULTIPROC_METHOD=spawn
-              pytest -s -v tests/e2e/offline_inference/test_voxcpm2_tts.py tests/e2e/online_serving/test_voxcpm2_tts.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-            "
-        mirror_hardwares: l4_1
-
-      - label: "Diffusion · Qwen Image Edit Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen_image_edit.py
-          - vllm_omni/diffusion/models/qwen_image/
-        timeout_in_minutes: 20
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_qwen_image_edit.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-        mirror_hardwares: h100_1
-      - label: "Diffusion · Bagel Test"
-        source_file_dependencies:
-          - tests/e2e/offline_inference/test_bagel.py
-          - tests/e2e/online_serving/test_bagel.py
-          - vllm_omni/model_executor/models/bagel/
-          - vllm_omni/diffusion/models/bagel/
-          - vllm_omni/model_executor/stage_input_processors/bagel.py
-          - vllm_omni/deploy/bagel.yaml
-        timeout_in_minutes: 20
-        commands:
-          - pytest -s -v tests/e2e/offline_inference/test_bagel.py tests/e2e/online_serving/test_bagel.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · Qwen Image Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen_image.py
-          - vllm_omni/diffusion/models/qwen_image/
-        commands:
-          - |
-            timeout 40m bash -c '
-              export VLLM_IMAGE_FETCH_TIMEOUT=60
-              pytest -s -v tests/e2e/online_serving/test_qwen_image.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-            '
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · Qwen Image Layered Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen_image_layered.py
-          - vllm_omni/diffusion/models/qwen_image/
-        commands:
-          - |
-            timeout 40m bash -c "
-              export VLLM_IMAGE_FETCH_TIMEOUT=60
-              pytest -s -v tests/e2e/online_serving/test_qwen_image_layered.py -m 'advanced_model and cuda' --run-level 'advanced_model'
-            "
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · Wan22 Test"
-        source_file_dependencies:
-          - tests/e2e/offline_inference/test_wan22_t2v.py
-          - tests/e2e/online_serving/test_wan22_t2v.py
-          - vllm_omni/diffusion/models/wan2_2/
-        commands:
-          - |
-            timeout 40m bash -c "
-              export VLLM_IMAGE_FETCH_TIMEOUT=60
-              pytest -s -v tests/e2e/offline_inference/test_wan22_t2v.py tests/e2e/online_serving/test_wan22_t2v.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model'
-            "
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · Z Image Test"
-        source_file_dependencies:
-          - tests/e2e/offline_inference/test_z_image.py
-          - tests/e2e/online_serving/test_z_image.py
-          - vllm_omni/diffusion/models/z_image/
-        timeout_in_minutes: 30
-        commands:
-          - pytest -s -v tests/e2e/offline_inference/test_z_image.py tests/e2e/online_serving/test_z_image.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model'
-        mirror_hardwares: l4_1
-      - label: "Diffusion · FLUX.2 Klein Test"
-        source_file_dependencies:
-          - tests/e2e/offline_inference/test_flux2_klein.py
-          - vllm_omni/diffusion/models/flux2_klein/
-        timeout_in_minutes: 30
-        commands:
-          - pytest -s -v tests/e2e/offline_inference/test_flux2_klein.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model'
-        mirror_hardwares: l4_1

.buildkite/cuda/test-nightly.yml

@@ -1,611 +0,0 @@
-env:
-  VLLM_WORKER_MULTIPROC_METHOD: spawn
-  VLLM_USE_FLASHINFER_MOE_FP16: 0
-  HF_HUB_DOWNLOAD_TIMEOUT: 300
-  HF_HUB_ETAG_TIMEOUT: 60
-
-steps:
-  # Group: collapses under one heading in the Buildkite UI; child steps still run in parallel.
-  - group: ":card_index_dividers: Omni Model Test"
-    key: nightly-omni-test-group
-    depends_on: upload-nightly-pipeline
-    if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test" || build.pull_request.labels includes "omni-test"
-    steps:
-
-      - label: ":full_moon: Omni · Function Test with H100"
-        timeout_in_minutes: 120
-        commands:
-          - pytest -sv tests/e2e --run-level "full_model" -m "full_model and H100 and omni" --ignore=tests/e2e/accuracy --ignore=tests/e2e/online_serving/test_qwen3_omni_multi_replicas.py --ignore=tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 Duplex Test"
-        timeout_in_minutes: 50
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py -m "full_model and cuda and H100 and omni" --run-level "full_model"
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: Omni · Doc Test with L4"
-        timeout_in_minutes: 90
-        commands:
-          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-          - pytest -s -v tests/examples/ -m "full_model and omni and L4" --run-level "full_model"
-        mirror_hardwares: l4_4
-
-      - label: ":full_moon: Omni · Doc Test with H100"
-        timeout_in_minutes: 90
-        commands:
-          - pytest -s -v tests/examples/ -m "full_model and omni and H100" --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Omni · Accuracy Test"
-        timeout_in_minutes: 180
-        commands:
-          - export SEED_TTS_WER_EVAL=1
-          - export SEED_TTS_EVAL_DEVICE=cuda:1
-          - |
-            set +e
-            pytest -s -v tests/e2e/accuracy/qwen3_omni/test_qwen3_omni.py -m "full_model" --run-level full_model
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/e2e/accuracy/qwen3_omni/results/qwen_omni_acc/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 · Accuracy Test"
-        timeout_in_minutes: 180
-        commands:
-          - export SEED_TTS_WER_EVAL=1
-          - export SEED_TTS_EVAL_DEVICE=cuda:1
-          - |
-            set +e
-            pytest -s -v tests/e2e/accuracy/minicpmo_4_5/test_minicpmo_4_5.py -m "full_model and cuda" --run-level full_model
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/e2e/accuracy/minicpmo_4_5/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Omni · Perf Test · No Async Chunk"
-        key: nightly-omni-performance-no-async-chunk
-        timeout_in_minutes: 300
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen3_omni_no_async_chunk.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Omni · Perf Test · Async Chunk"
-        key: nightly-omni-performance-async-chunk
-        timeout_in_minutes: 180
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Omni · Perf Test · vLLM Text"
-        key: nightly-omni-performance-vllm-text
-        timeout_in_minutes: 180
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen3_omni_vllm_text.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Omni · Perf Test · Multi-Replica"
-        key: nightly-omni-performance-multi-replicas
-        timeout_in_minutes: 180
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen3_omni_multi_replicas.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_3
-
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 · Perf Test"
-        key: nightly-omni-performance-minicpmo-4-5
-        timeout_in_minutes: 180
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_minicpmo_4_5.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 · Duplex Seed-TTS Perf Test"
-        key: nightly-omni-performance-minicpmo-4-5-duplex-seed-tts
-        timeout_in_minutes: 180
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_minicpmo_4_5_duplex_seed_tts.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: Omni · Multi-Replica Startup Test with 4x H100"
-        timeout_in_minutes: 45
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_qwen3_omni_multi_replicas.py -m "full_model" --run-level "core_model"
-        mirror_hardwares: h100_4
-
-  - group: ":card_index_dividers: TTS Model Test"
-    key: nightly-tts-test-group
-    depends_on: upload-nightly-pipeline
-    if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test" || build.pull_request.labels includes "tts-test"
-    steps:
-
-      - label: ":full_moon: TTS · Function Test with L4"
-        timeout_in_minutes: 120
-        commands:
-          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-          - export VLLM_USE_DEEP_GEMM="0"
-          - export VLLM_MOE_USE_DEEP_GEMM="0"
-          - pytest -s -v tests/e2e/ -m "full_model and L4 and tts" --run-level "full_model" --ignore=tests/e2e/accuracy --ignore=tests/e2e/online_serving/test_voxcpm2_tts_expansion.py
-        mirror_hardwares: l4_1
-
-      - label: ":full_moon: TTS · Accuracy Test · VoxCPM2"
-        timeout_in_minutes: 30
-        commands:
-          - |
-            timeout 30m bash -c "
-              export VLLM_LOGGING_LEVEL=DEBUG
-              export VLLM_WORKER_MULTIPROC_METHOD=spawn
-              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
-              pytest -s -v tests/e2e/online_serving/test_voxcpm2_tts_expansion.py -m 'full_model and cuda and tts' --run-level 'full_model'
-            "
-        mirror_hardwares: l4_1
-
-      - label: ":full_moon: TTS · Perf Test"
-        key: nightly-tts-performance
-        timeout_in_minutes: 180
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_tts.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: TTS · VoxCPM2 · Perf Test"
-        key: nightly-tts-performance-voxcpm2
-        timeout_in_minutes: 180
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_voxcpm2.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: TTS · Higgs-Audio-V3 · Perf Test"
-        key: nightly-tts-performance-higgs-audio-v3
-        timeout_in_minutes: 180
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - export VLLM_USE_DEEP_GEMM="0"
-          - export VLLM_MOE_USE_DEEP_GEMM="0"
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_higgs_audio_v3.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-        mirror_hardwares: h100_1
-
-  - group: ":card_index_dividers: Tiny Model Tests [Multi-GPU]"
-    key: nightly-tiny-model-test-group
-    depends_on: upload-nightly-pipeline
-    if: >-
-      build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test"
-    steps:
-
-      - label: ":full_moon: Tiny Model Tests · Diffusion (Multi-GPU accelerations)"
-        timeout_in_minutes: 30
-        # NOTE: Single-GPU (core_model) tiny model tests run on the ready label,
-        # so nightly only adds the multi-GPU parallelism configurations.
-        #
-        # This is a bit confusing, but `full_model` is used to mark the multigpu tests, and
-        # --run-level `core_model` is used to indicate that we should use tiny model weights
-        # for the CI, since these tests should pass irrespective of whether or not we use
-        # the full weights or not.
-        commands:
-          - timeout 25m pytest -sv tests/model_tests/diffusion -m 'full_model and cuda' --run-level "core_model"
-        mirror_hardwares: l4_4
-
-  - group: ":card_index_dividers: Diffusion X2I(&A&T) Model Test"
-    key: nightly-diffusion-x2iat-group
-    depends_on: upload-nightly-pipeline
-    if: >-
-      build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test" ||
-      build.pull_request.labels includes "diffusion-x2iat-test"
-    steps:
-      # Use explicit file shards so single-card cases do not reserve 2+ GPUs,
-      # and Bagel feature coverage is not duplicated via a broad tests/e2e sweep.
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Function Test with H100 · Single-GPU"
-        timeout_in_minutes: 120
-        commands:
-          - >-
-            pytest -sv
-            tests/e2e/online_serving/test_qwen_image_expansion.py
-            tests/e2e/online_serving/test_qwen_image_edit_expansion.py
-            tests/e2e/online_serving/test_qwen_image_layered_expansion.py
-            tests/e2e/online_serving/test_boogu_image.py
-            tests/e2e/online_serving/test_boogu_image_edit.py
-            tests/e2e/online_serving/test_boogu_image_expansion.py
-            tests/e2e/online_serving/test_boogu_image_edit_expansion.py
-            tests/e2e/online_serving/test_bagel_expansion.py
-            tests/e2e/online_serving/test_krea2_expansion.py
-            tests/e2e/offline_inference/test_krea2_expansion.py
-            -m "full_model and diffusion and H100 and not distributed_cuda"
-            --run-level "full_model"
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Function Test with H100 · Multi-GPU Qwen-Image"
-        timeout_in_minutes: 120
-        commands:
-          - >-
-            pytest -sv
-            tests/e2e/online_serving/test_qwen_image_expansion.py
-            tests/e2e/online_serving/test_qwen_image_edit_expansion.py
-            tests/e2e/offline_inference/test_krea2_expansion.py
-            -m "full_model and diffusion and H100 and distributed_cuda"
-            --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Function Test with H100 · Multi-GPU Layered/LongCat/FLUX"
-        timeout_in_minutes: 90
-        commands:
-          - >-
-            pytest -sv
-            tests/e2e/online_serving/test_qwen_image_layered_expansion.py
-            -m "full_model and diffusion and H100 and distributed_cuda"
-            --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Function Test with H100 · Multi-GPU Bagel"
-        timeout_in_minutes: 120
-        commands:
-          - >-
-            pytest -sv
-            tests/e2e/online_serving/test_bagel_expansion.py
-            -m "full_model and diffusion and H100 and distributed_cuda"
-            --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · GLM-Image Function Test with H100"
-        timeout_in_minutes: 120
-        commands:
-          - >-
-            pytest -sv
-            tests/e2e/online_serving/test_glm_image_expansion.py
-            tests/e2e/offline_inference/test_glm_image_autoround_w4a16_expansion.py
-            -m "full_model and diffusion and H100"
-            --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Function Test with L4"
-        timeout_in_minutes: 120
-        commands:
-          - pytest -sv tests/e2e/ -k "not test_wan and not test_bagel_expansion and not hunyuan" -m "full_model and diffusion and L4" --run-level "full_model" --ignore=tests/e2e/accuracy
-        mirror_hardwares: l4_4
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Doc Test"
-        timeout_in_minutes: 60
-        commands:
-          - pytest -s -v tests/examples/*/test_text_to_image.py -m "full_model and example and H100" --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Accuracy Test"
-        timeout_in_minutes: 180
-        commands:
-          - export VLLM_HTTP_TIMEOUT_KEEP_ALIVE=120
-          - pytest -s -v tests/e2e/accuracy/test_qwen_image*.py --run-level full_model
-          - pytest -s -v tests/e2e/accuracy/test_diffusers_backend_similarity.py -k '2i_matches_diffusers' -m full_model --run-level full_model
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: HunyuanImage3-DIT · Accuracy Test"
-        timeout_in_minutes: 180
-        commands:
-          - export HUNYUAN_IMAGE3_MODEL="tencent/HunyuanImage-3.0-Instruct"
-          - export HUNYUAN_IMAGE3_DEVICES="0,1,2,3"
-          - pytest -s -v tests/e2e/accuracy/test_hunyuan_image3_pixel_accuracy.py -m full_model --run-level full_model
-        mirror_hardwares: h100_4
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image"
-        key: nightly-diffusion-x2iat-performance-qwen-image
-        timeout_in_minutes: 180
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - export DIFFUSION_ATTENTION_BACKEND=FLASH_ATTN
-          - export CACHE_DIT_VERSION=1.5.0
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen_image_vllm_omni.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT
-        mirror_hardwares: h100_4
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image-Edit"
-        key: nightly-diffusion-x2iat-performance-qwen-image-edit
-        timeout_in_minutes: 180
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - export DIFFUSION_ATTENTION_BACKEND=FLASH_ATTN
-          - export CACHE_DIT_VERSION=1.5.0
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen_image_edit_vllm_omni.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT
-        mirror_hardwares: h100_4
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image-Edit-2511"
-        key: nightly-diffusion-x2iat-performance-qwen-image-edit-2511
-        timeout_in_minutes: 180
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - export DIFFUSION_ATTENTION_BACKEND=FLASH_ATTN
-          - export CACHE_DIT_VERSION=1.5.0
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen_image_edit_2511_vllm_omni.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT
-        mirror_hardwares: h100_4
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image-Layered"
-        key: nightly-diffusion-x2iat-performance-qwen-image-layered
-        timeout_in_minutes: 120
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - export DIFFUSION_ATTENTION_BACKEND=FLASH_ATTN
-          - export CACHE_DIT_VERSION=1.5.0
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen_image_layered_vllm_omni.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · BAGEL"
-        key: nightly-diffusion-x2iat-performance-bagel
-        timeout_in_minutes: 180
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - export DIFFUSION_ATTENTION_BACKEND=FLASH_ATTN
-          - export CACHE_DIT_VERSION=1.5.0
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_bagel_vllm_omni.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT
-        mirror_hardwares: h100_1
-
-  - group: ":card_index_dividers: Diffusion X2V Model Test"
-    key: nightly-diffusion-x2v-group
-    depends_on: upload-nightly-pipeline
-    if: >-
-      build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test" ||
-      build.pull_request.labels includes "diffusion-x2v-test"
-    steps:
-
-      - label: ":full_moon: Diffusion X2V · Wan2.2 T2V Function Test"
-        timeout_in_minutes: 90
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "t2v" -m "full_model and cuda" --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2V · Wan2.2 I2V/TI2V Function Test"
-        timeout_in_minutes: 90
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "i2v" -m "full_model and cuda" --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2V · LingBot Video MoE Function Test"
-        timeout_in_minutes: 90
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_lingbot_video_moe.py -k "video_generation" -m "full_model and cuda" --run-level "full_model"
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: Diffusion X2V · Doc Test"
-        timeout_in_minutes: 60
-        commands:
-          - pytest -s -v tests/examples/offline_inference/test_image_to_video.py -m "full_model and example and H100" --run-level "full_model"
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: Diffusion X2V · Other Function Test"
-        timeout_in_minutes: 90
-        commands:
-          - pytest -s -v tests/e2e/offline_inference/test_wan22_autoround_w4a16_expansion.py -m "full_model and cuda" --run-level "full_model"
-          - pytest -s -v tests/e2e/online_serving/test_wan_2_1_vace_expansion.py tests/e2e/online_serving/test_ltx2_expansion.py -m "full_model and cuda" --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2V · Wan2.2 Accuracy Test"
-        timeout_in_minutes: 180
-        commands:
-          - pytest -s -v tests/e2e/accuracy/wan22_i2v/test_wan22_i2v_video_similarity.py -m full_model --run-level full_model
-          - pytest -s -v tests/e2e/accuracy/test_diffusers_backend_similarity.py -k '2v_matches_diffusers' -m full_model --run-level full_model
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2V · MiniMax H3 I2VA/Ref2VA Accuracy Test"
-        timeout_in_minutes: 180
-        commands:
-          - pytest -s -v tests/e2e/accuracy/minimax_h3/test_minimax_h3_i2va_ref2va_similarity.py -m full_model --run-level full_model
-        mirror_hardwares: h100_4
-
-      - label: ":full_moon: Diffusion X2V · Other Accuracy Test"
-        timeout_in_minutes: 180
-        commands:
-          - pytest -s -v tests/e2e/accuracy/hunyuanvideo15_t2v/test_hunyuanvideo15_t2v_video_similarity.py -m full_model --run-level full_model
-          - pytest -s -v tests/e2e/accuracy/hunyuanvideo15_i2v/test_hunyuanvideo15_i2v_video_similarity.py -m full_model --run-level full_model
-          - pytest -s -v 'tests/e2e/accuracy/ltx/test_ltx_official_similarity.py::test_ltx_one_stage_matches_official[ltx2_3_i2v]' -m full_model --run-level full_model
-          - pytest -s -v tests/e2e/accuracy/test_video_streaming_output_similarity.py -m full_model --run-level full_model
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2V · Perf Test"
-        key: nightly-diffusion-x2v-performance
-        timeout_in_minutes: 180
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - export DIFFUSION_ATTENTION_BACKEND=FLASH_ATTN
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_wan22_i2v_vllm_omni.json
-            EXIT1=$$?
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_cosmos3_vllm_omni.json
-            EXIT2=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            if [ $$EXIT1 -ne 0 ]; then exit $$EXIT1; fi
-            exit $$EXIT2
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion X2V · Perf Test · MiniMax-H3"
-        key: nightly-diffusion-x2v-performance-minimax-h3
-        timeout_in_minutes: 180
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - export DIFFUSION_ATTENTION_BACKEND=FLASH_ATTN
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_minimax_h3_vllm_omni.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT
-        mirror_hardwares: h100_4
-
-  - group: ":card_index_dividers: Diffusion Test"
-    key: nightly-diffusion-test-group
-    depends_on: upload-nightly-pipeline
-    if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
-    steps:
-      - label: ":full_moon: Diffusion · Distributed Test with L4"
-        timeout_in_minutes: 60
-        commands:
-          - pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4' --run-level "full_model"
-        mirror_hardwares: l4_4
-
-      - label: ":full_moon: Diffusion · Distributed Test with H100"
-        timeout_in_minutes: 60
-        commands:
-          - pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and H100' --run-level "full_model"
-        mirror_hardwares: h100_4
-
-      - label: ":full_moon: Diffusion · Offloader Test"
-        timeout_in_minutes: 60
-        commands:
-          - pytest -sv tests/diffusion/offloader -m "full_model and cuda"
-        mirror_hardwares: l4_1
-
-      - label: ":full_moon: Diffusion · Quantization Test with H100 · Single-GPU"
-        timeout_in_minutes: 60
-        commands:
-          - pytest -sv tests/diffusion/quantization -m 'full_model and cuda and H100' --run-level "full_model"
-        mirror_hardwares: h100_1
-
-      - label: ":full_moon: Diffusion · MiniMax H3 FP8 Quality Test with H100 · 2-GPU"
-        timeout_in_minutes: 60
-        commands:
-          - pytest -sv tests/diffusion/models/minimax_h3/test_minimax_h3_quantization_quality.py -m 'full_model and cuda and H100' --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: ":full_moon: Diffusion · Quantization Test with L4"
-        timeout_in_minutes: 60
-        commands:
-          - pip install "vllm-gguf-plugin>=0.0.3"
-          - pytest -sv tests/diffusion/quantization -m 'full_model and cuda and L4' --run-level "full_model"
-        mirror_hardwares: l4_1
-
-  - label: ":bar_chart: Testcase Statistics"
-    key: nightly-testcase-statistics
-    timeout_in_minutes: 120
-    depends_on: upload-nightly-pipeline
-    if: build.env("NIGHTLY") == "1"
-    commands:
-      - python tools/nightly/buildkite_testcase_statistics.py -o tests/dfx/perf/results/buildkite_testcase_statistics.html
-      - buildkite-agent artifact upload "tests/dfx/perf/results/*.html"
-    mirror_hardwares: h100_1
-
-  # NOTE: ":email: Nightly Collection & Email" is deprecated and will be removed soon.
-  # Do not add new depends_on entries or extend this step.
-  - label: ":email: Nightly Collection & Email"
-    key: nightly-perf-distribution
-    depends_on:
-      - nightly-omni-performance-no-async-chunk
-      - nightly-omni-performance-async-chunk
-      - nightly-omni-performance-vllm-text
-      - nightly-omni-performance-multi-replicas
-      - nightly-tts-performance
-      - nightly-tts-performance-higgs-audio-v3
-      - nightly-diffusion-x2iat-performance-qwen-image
-      - nightly-diffusion-x2iat-performance-qwen-image-edit
-      - nightly-diffusion-x2iat-performance-qwen-image-edit-2511
-      - nightly-diffusion-x2iat-performance-qwen-image-layered
-      - nightly-diffusion-x2iat-performance-bagel
-      - nightly-diffusion-x2v-performance
-      - nightly-testcase-statistics
-    if: build.env("NIGHTLY") == "1" && build.env("EMAIL_DISTRIBUTION") == "1"
-    commands:
-      - pip install openpyxl
-      - export DEFAULT_INPUT_DIR=tests/dfx/perf/results
-      - export DEFAULT_OUTPUT_DIR=tests/dfx/perf/results
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-tts-performance
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-tts-performance-higgs-audio-v3
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-omni-performance-no-async-chunk
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-omni-performance-async-chunk
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-omni-performance-vllm-text
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-omni-performance-multi-replicas
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-diffusion-x2iat-performance-qwen-image
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-diffusion-x2iat-performance-qwen-image-edit
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-diffusion-x2iat-performance-qwen-image-edit-2511
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-diffusion-x2iat-performance-qwen-image-layered
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-diffusion-x2iat-performance-bagel
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-diffusion-x2v-performance
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.html" . --step nightly-testcase-statistics
-      - python tools/nightly/generate_nightly_perf_excel.py
-      - python tools/nightly/generate_nightly_perf_html.py
-      - python tools/nightly/send_nightly_email.py --report-file "tests/dfx/perf/results/*.xlsx, tests/dfx/perf/results/*.html"
-      - buildkite-agent artifact upload "tests/dfx/perf/results/*.xlsx"
-      - buildkite-agent artifact upload "tests/dfx/perf/results/*.html"
-    agents:
-      queue: "cpu_queue_premerge"

.buildkite/cuda/test-ready.yml

@@ -1,375 +0,0 @@
-env:
-  VLLM_WORKER_MULTIPROC_METHOD: spawn
-  VLLM_USE_FLASHINFER_MOE_FP16: 0
-  HF_HUB_DOWNLOAD_TIMEOUT: 300
-  HF_HUB_ETAG_TIMEOUT: 60
-
-steps:
-  - group: ":card_index_dividers: Simple Test"
-    depends_on: upload-ready-pipeline
-    steps:
-      - label: "Simple · Model Executor Test"
-        commands:
-          - "timeout 20m pytest -sv tests/model_executor -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-        mirror_hardwares: l4_1
-
-      - label: "Simple · Diffusion Test"
-        commands:
-          - "timeout 20m pytest -sv tests/diffusion -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-        mirror_hardwares: l4_1
-
-      - label: "Simple · Engine&Entrypoints Test"
-        commands:
-          - "timeout 20m pytest -sv tests/entrypoints tests/engine -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-        mirror_hardwares: l4_1
-
-      - label: "Simple · Other Test"
-        commands:
-          - "timeout 20m pytest -sv tests/ -m 'core_model and cpu' --ignore=tests/diffusion --ignore=tests/model_executor --ignore=tests/entrypoints --ignore=tests/engine --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
-        mirror_hardwares: l4_1
-
-  - group: ":card_index_dividers: Diffusion Test"
-    depends_on: upload-ready-pipeline
-    steps:
-
-      - label: "Diffusion · Offloader Test"
-        commands:
-          - timeout 40m pytest -s -v tests/diffusion/offloader -m "core_model and cuda" --run-level "core_model"
-        mirror_hardwares: l4_1
-
-      - label: "Diffusion · Cache Test"
-        commands:
-          - timeout 15m pytest -sv tests/diffusion/cache -m 'core_model and cuda' --run-level "core_model"
-        mirror_hardwares: l4_1
-
-      - label: "Diffusion · Batch Test"
-        commands:
-          - timeout 15m pytest -sv tests/diffusion/batching -m 'core_model and cuda' --run-level "core_model"
-        mirror_hardwares: l4_1
-
-      - label: "Diffusion · Distributed & Attention Test"
-        source_file_dependencies:
-          - tests/diffusion/distributed/
-          - tests/diffusion/attention/test_attention_sp.py
-          - vllm_omni/diffusion/distributed/
-          - vllm_omni/diffusion/attention/
-          - vllm_omni/diffusion/data.py
-          - vllm_omni/diffusion/models/
-        commands:
-          - timeout 20m pytest -sv tests/diffusion/distributed -m 'core_model and cuda' --run-level "core_model"
-          - timeout 20m pytest -sv tests/diffusion/attention/test_attention_sp.py -m 'core_model and cuda' --run-level "core_model"
-        mirror_hardwares: l4_4
-
-      - label: "Diffusion · Model Test"
-        commands:
-          - timeout 15m pytest -sv tests/diffusion/models/ -m 'core_model and cuda' --run-level "core_model"
-        mirror_hardwares: l4_1
-
-      - label: "Diffusion · Other Test"
-        commands:
-          - timeout 15m pytest -sv tests/diffusion/*.py -m 'core_model and cuda' --run-level "core_model"
-        mirror_hardwares: l4_1
-
-  - group: ":card_index_dividers: Tiny Model Tests [Single GPU]"
-    depends_on: upload-ready-pipeline
-    steps:
-
-      - label: "Tiny Model Tests · Diffusion (base)"
-        commands:
-          - timeout 15m pytest -sv tests/model_tests/diffusion -m 'core_model and cuda' --run-level "core_model"
-        mirror_hardwares: l4_1
-
-  - label: "Engine&Model Executor Test"
-    depends_on: upload-ready-pipeline
-    commands:
-      - |
-        timeout 15m bash -c "
-                  pytest -sv tests/engine/ tests/model_executor/ -m 'core_model and cuda' --run-level 'core_model'
-        "
-    mirror_hardwares: l4_1
-
-  - label: "Distributed Test"
-    depends_on: upload-ready-pipeline
-    commands:
-      - |
-        timeout 20m bash -c "
-          pytest -sv tests/distributed/ -m 'core_model and cuda and L4' --run-level 'core_model'
-        "
-    mirror_hardwares: l4_1
-
-  - label: "Entrypoints Test"
-    depends_on: upload-ready-pipeline
-    commands:
-      - |
-        timeout 30m bash -c "
-          export VLLM_WORKER_MULTIPROC_METHOD=spawn
-          pytest -sv tests/entrypoints/ -m 'core_model and cuda' --run-level 'core_model'
-        "
-    mirror_hardwares: l4_1
-
-  - group: ":card_index_dividers: E2E Test"
-    depends_on: upload-ready-pipeline
-    steps:
-      - label: "Custom Pipeline Test"
-        source_file_dependencies:
-          - tests/e2e/features/custom_pipeline/
-          - tests/e2e/features/helpers/custom_pipeline.py
-          - vllm_omni/diffusion/
-          - vllm_omni/engine/
-          - vllm_omni/entrypoints/
-          - vllm_omni/inputs/
-          - vllm_omni/outputs/
-        commands:
-          - timeout 20m pytest -s -v tests/e2e/features/custom_pipeline/ -m "core_model"
-        agents:
-          queue: "gpu_1_queue"
-        plugins:
-          - docker#v5.2.0:
-              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-              always-pull: true
-              propagate-environment: true
-              # vLLM 0.27 added a pre-flight capacity check in
-              # distributed/device_communicators/shm_broadcast.py. Without this
-              # the container gets Docker's 64 MiB default and every test in
-              # this step dies at engine start with
-              #   RuntimeError: Insufficient space in /dev/shm:
-              #                 240 MiB required, 64 MiB available
-              # (9 failed in 8.7s on build #2949). vLLM 0.26 had no such check
-              # and allocated regardless, so this step passed on main while
-              # being under-provisioned the whole time — 0.27 turned a silent
-              # risk into an explicit error.
-              #
-              # This is the only inline docker plugin block in .buildkite/cuda/;
-              # every other step inherits common/ci_mirror_hardwares.yml, which
-              # already sets 8gb. Matching that rather than inventing a value.
-              shm-size: "8gb"
-              environment:
-                - "HF_HOME=/fsx/hf_cache"
-              volumes:
-                - "/fsx/hf_cache:/fsx/hf_cache"
-
-      - label: "RLHF · VeRL-Omni E2E Test"
-        source_file_dependencies:
-          - tests/e2e/features/rlhf_test/test_verl_omni_e2e.py
-          - tests/e2e/features/helpers/verl_omni_server.py
-          - tests/e2e/features/helpers/custom_pipeline.py
-          - vllm_omni/diffusion/
-          - vllm_omni/engine/
-          - vllm_omni/entrypoints/
-          - vllm_omni/inputs/
-          - vllm_omni/outputs/
-        commands:
-          - |
-            timeout 20m bash -c "
-              pytest -s -v tests/e2e/features/rlhf_test/test_verl_omni_e2e.py
-            "
-        mirror_hardwares: l4_1
-
-      - label: "Omni · Qwen3-Omni Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen3_omni.py
-          - vllm_omni/model_executor/models/qwen3_omni/
-          - vllm_omni/model_executor/stage_input_processors/qwen3_omni.py
-          - vllm_omni/deploy/qwen3_omni_moe.yaml
-        commands:
-          - |
-            timeout 20m bash -c "
-              pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: h100_2
-
-      - label: "Omni · MiniCPM-o 4.5 Offline Test"
-        source_file_dependencies:
-          - tests/e2e/offline_inference/test_minicpmo_4_5.py
-          - vllm_omni/deploy/minicpmo_4_5.yaml
-        commands:
-          - |
-            timeout 20m bash -c "
-              pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: h100_1
-
-      - label: "Omni · MiniCPM-o 4.5 Online Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_minicpmo_4_5.py
-          - vllm_omni/deploy/minicpmo_4_5.yaml
-        commands:
-          - |
-            timeout 20m bash -c "
-              pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: h100_1
-
-      - label: "Omni · MiniCPM-o 4.5 Duplex Test"
-        source_file_dependencies:
-          - tests/assets/minicpmo_4_5/response_required_16k.wav
-          - tests/assets/minicpmo_4_5/soft_interrupt_16k.wav
-          - tests/e2e/online_serving/test_minicpmo_4_5_duplex.py
-          - tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
-          - tests/e2e/online_serving/test_minicpmo_realtime_duplex_drivers.py
-          - tests/e2e/online_serving/helpers/minicpmo_realtime_duplex_scenarios.py
-          - tests/e2e/online_serving/run_minicpmo_realtime_duplex_multi_session.py
-          - tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py
-          - tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py
-          - vllm_omni/deploy/minicpmo_4_5_duplex.yaml
-          - vllm_omni/experimental/fullduplex/
-          - vllm_omni/model_executor/models/minicpmo_4_5/
-          - vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
-          - vllm_omni/core/sched/
-          - vllm_omni/outputs/multimodal_accumulation.py
-          - vllm_omni/engine/stage_init_utils.py
-          - vllm_omni/engine/async_omni_engine.py
-          - vllm_omni/entrypoints/cli/serve.py
-        commands:
-          - |
-            timeout 20m bash -c "
-              pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex.py -m 'core_model and cuda' --run-level 'core_model'
-            "
-        mirror_hardwares: h100_1
-
-      - label: "Omni · MiniCPM-o 4.5 Perf Test"
-        timeout_in_minutes: 60
-        source_file_dependencies:
-          - tests/dfx/perf/tests/test_minicpmo_4_5_ready.json
-          - vllm_omni/deploy/minicpmo_4_5.yaml
-          - vllm_omni/model_executor/models/minicpmo_4_5/
-          - vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_minicpmo_4_5_ready.json -m 'core_model and cuda'
-        mirror_hardwares: h100_1
-
-      - label: "TTS · VoxCPM2 Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_voxcpm2_tts.py
-          - vllm_omni/model_executor/models/voxcpm2/
-          - vllm_omni/deploy/voxcpm2.yaml
-        timeout_in_minutes: 30
-        commands:
-          - |
-            timeout 30m bash -c "
-              export VLLM_LOGGING_LEVEL=DEBUG
-              export VLLM_WORKER_MULTIPROC_METHOD=spawn
-              pytest -s -v tests/e2e/online_serving/test_voxcpm2_tts.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: l4_1
-
-      - label: "TTS · Qwen3-TTS CustomVoice Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen3_tts_customvoice.py
-          - vllm_omni/model_executor/models/qwen3_tts/
-          - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
-          - vllm_omni/deploy/qwen3_tts.yaml
-        commands:
-          - |
-            timeout 20m bash -c "
-              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
-              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: l4_1
-
-      - label: "TTS · Qwen3-TTS Base Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen3_tts_base.py
-          - vllm_omni/model_executor/models/qwen3_tts/
-          - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
-          - vllm_omni/deploy/qwen3_tts.yaml
-        commands:
-          - |
-            timeout 20m bash -c "
-              export VLLM_WORKER_MULTIPROC_METHOD=spawn
-              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
-              export VLLM_OMNI_USE_V2_RUNNER=1
-              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: l4_1
-
-      - label: "TTS · Higgs-Audio-V3 Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_higgs_audio_v3.py
-          - vllm_omni/model_executor/models/higgs_audio_v3/
-          - vllm_omni/model_executor/stage_input_processors/higgs_audio_v3.py
-          - vllm_omni/deploy/higgs_multimodal_qwen3.yaml
-        commands:
-          - |
-            timeout 20m bash -c "
-              export VLLM_WORKER_MULTIPROC_METHOD=spawn
-              export VLLM_USE_DEEP_GEMM=0
-              export VLLM_MOE_USE_DEEP_GEMM=0
-              pytest -s -v tests/e2e/online_serving/test_higgs_audio_v3.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: l4_1
-
-      - label: "Diffusion · Qwen Image Edit Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen_image_edit.py
-          - vllm_omni/diffusion/models/qwen_image/
-        commands:
-          - |
-            timeout 20m bash -c "
-              pytest -s -v tests/e2e/online_serving/test_qwen_image_edit.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · Bagel Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_bagel.py
-          - vllm_omni/model_executor/models/bagel/
-          - vllm_omni/diffusion/models/bagel/
-          - vllm_omni/model_executor/stage_input_processors/bagel.py
-          - vllm_omni/deploy/bagel.yaml
-        commands:
-          - |
-            timeout 40m bash -c "
-              export VLLM_IMAGE_FETCH_TIMEOUT=60
-              pytest -s -v tests/e2e/online_serving/test_bagel.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · Wan22 Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_wan22_t2v.py
-          - vllm_omni/diffusion/models/wan2_2/
-        commands:
-          - |
-            timeout 40m bash -c "
-              export VLLM_IMAGE_FETCH_TIMEOUT=60
-              pytest -s -v tests/e2e/online_serving/test_wan22_t2v.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · Cosmos3 Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_cosmos3.py
-          - vllm_omni/diffusion/models/cosmos3/
-        commands:
-          - |
-            timeout 40m bash -c "
-              export VLLM_IMAGE_FETCH_TIMEOUT=60
-              pytest -s -v tests/e2e/online_serving/test_cosmos3.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · Qwen Image Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen_image.py
-          - vllm_omni/diffusion/models/qwen_image/
-        commands:
-          - |
-            timeout 40m bash -c "
-              export VLLM_IMAGE_FETCH_TIMEOUT=60
-              pytest -s -v tests/e2e/online_serving/test_qwen_image.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · Qwen Image Layered Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen_image_layered.py
-          - vllm_omni/diffusion/models/qwen_image/
-        commands:
-          - |
-            timeout 40m bash -c "
-              export VLLM_IMAGE_FETCH_TIMEOUT=60
-              pytest -s -v tests/e2e/online_serving/test_qwen_image_layered.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: h100_1

.buildkite/cuda/test-weekly.yml

@@ -1,136 +0,0 @@
-env:
-  VLLM_WORKER_MULTIPROC_METHOD: spawn
-  VLLM_USE_FLASHINFER_MOE_FP16: 0
-  HF_HUB_DOWNLOAD_TIMEOUT: 300
-  HF_HUB_ETAG_TIMEOUT: 60
-
-steps:
-
-  - label: "Reliability Test - qwen3-omni"
-    timeout_in_minutes: 180
-    depends_on: upload-weekly-pipeline
-    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
-    commands:
-      - pytest -s -v tests/dfx/reliability/test_reliability_qwen3_omni.py -m "slow"
-    mirror_hardwares: h100_2
-
-  - label: "Reliability Test - wan22"
-    timeout_in_minutes: 180
-    depends_on: upload-weekly-pipeline
-    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
-    commands:
-      - pytest -s -v tests/dfx/reliability/test_reliability_wan22.py -m "slow"
-    mirror_hardwares: h100_2
-
-  - label: "Reliability Test - hunyuan-image"
-    timeout_in_minutes: 180
-    depends_on: upload-weekly-pipeline
-    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
-    commands:
-      - pytest -s -v tests/dfx/reliability/test_reliability_hunyuan_image.py -m "slow"
-    mirror_hardwares: h100_4
-
-  - label: "Reliability Test - voxcpm2"
-    timeout_in_minutes: 180
-    depends_on: upload-weekly-pipeline
-    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
-    commands:
-      - pytest -s -v tests/dfx/reliability/test_reliability_voxcpm2.py -m "slow"
-    mirror_hardwares: l4_1
-
-  - group: "Reliability Test - Invalid parameters Test"
-    depends_on: upload-weekly-pipeline
-    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
-    steps:
-
-      - label: "Invalid parameters Test · H100"
-        timeout_in_minutes: 120
-        commands:
-          - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and H100"
-        mirror_hardwares: h100_2
-
-      - label: "Invalid parameters Test · L4"
-        timeout_in_minutes: 120
-        commands:
-          - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and L4"
-        mirror_hardwares: l4_1
-
-  - group: ":card_index_dividers: E2E Tests"
-    depends_on: upload-weekly-pipeline
-    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
-    steps:
-
-      - label: "Omni · L4"
-        timeout_in_minutes: 90
-        commands:
-          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-          - pytest -s -v tests/e2e/*/test_qwen2_5_omni_expansion.py --run-level "core_model"
-          - >-
-            pytest -s -v tests/e2e/
-            --ignore=tests/e2e/online_serving/test_qwen2_5_omni_expansion.py
-            --ignore=tests/e2e/offline_inference/test_qwen2_5_omni_expansion.py
-            -m "slow and L4 and omni"
-            --run-level "full_model"
-        mirror_hardwares: l4_4
-
-      - label: "Omni · H100"
-        timeout_in_minutes: 90
-        commands:
-          - >-
-            pytest -sv
-            tests/e2e/ -m "slow and H100 and omni"
-            --run-level "full_model"
-        mirror_hardwares: h100_2
-
-      - label: "TTS · L4"
-        timeout_in_minutes: 90
-        commands:
-          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-          - export VLLM_USE_DEEP_GEMM="0"
-          - export VLLM_MOE_USE_DEEP_GEMM="0"
-          - |
-            failed=0
-            for f in $(pytest --collect-only -q tests/e2e/ -m "slow and L4 and tts" --run-level "full_model" | grep '\.py::' | sed -E 's|::.*||' | sort -u); do
-              pytest -s -v "$$f" -m "slow and L4 and tts" --run-level "full_model" || failed=1
-            done
-            exit $$failed
-        mirror_hardwares: l4_1
-
-      - label: "TTS · H100"
-        timeout_in_minutes: 90
-        commands:
-          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-          - export VLLM_USE_DEEP_GEMM="0"
-          - export VLLM_MOE_USE_DEEP_GEMM="0"
-          - >-
-            pytest -sv
-            tests/e2e/ -m "slow and H100 and tts"
-            --run-level "full_model"
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · L4"
-        timeout_in_minutes: 60
-        commands:
-          - >-
-            pytest -sv
-            tests/e2e/ -m "slow and diffusion and L4"
-            --run-level "full_model"
-        mirror_hardwares: l4_4
-
-      - label: "Diffusion · H100 · Single-GPU"
-        timeout_in_minutes: 120
-        commands:
-          - >-
-            pytest -sv
-            tests/e2e/ -m "slow and diffusion and H100 and not distributed_cuda"
-            --run-level "full_model"
-        mirror_hardwares: h100_1
-
-      - label: "Diffusion · H100 · Multi-GPU"
-        timeout_in_minutes: 90
-        commands:
-          - >-
-            pytest -sv
-            tests/e2e/ -m "slow and diffusion and H100 and distributed_cuda"
-            --run-level "full_model"
-        mirror_hardwares: h100_2

.buildkite/intel/scripts/bootstrap-intel-omni.sh

@@ -1,16 +0,0 @@
-#!/bin/bash
-# vllm-omni Intel bootstrap
-# Uses static pipeline-intel.yml for Intel XPU tests
-
-set -euo pipefail
-
-source .buildkite/common/scripts/resolve_skip_ci.sh
-
-upload_pipeline() {
-    echo "--- 🛠 Preparing Intel pipeline"
-    buildkite-agent pipeline upload .buildkite/intel/pipeline-intel.yml
-}
-
-gate_bootstrap_ci intel l2
-
-upload_pipeline

.buildkite/intel/scripts/run-xpu-test.sh

@@ -1,94 +0,0 @@
-#!/bin/bash
-
-# This script build the XPU docker image and run the offline inference inside the container.
-set -ex
-
-omni_source_dir=$(git rev-parse --show-toplevel)
-
-base_image_name="xpu/vllm-omni-ci-base:${VLLM_VERSION:?VLLM_VERSION must be set}"
-image_name="xpu/vllm-omni-ci:${BUILDKITE_COMMIT:?BUILDKITE_COMMIT must be set}"
-container_name="xpu_${BUILDKITE_COMMIT}_$(
-    tr -dc A-Za-z0-9 </dev/urandom | head -c 10
-    echo
-)"
-
-cd "${omni_source_dir}"
-
-# The XPU base image is ~37GB; the default gzip layer exporter is single-threaded
-# and takes ~16min to compress it. zstd is multi-threaded (uses all cores) at a
-# similar ratio; set EXPORT_COMPRESSION=uncompressed to skip compression entirely
-# for local-only images. This requires the containerd image store (buildx docker
-# driver), which is the default here.
-EXPORT_COMPRESSION="${EXPORT_COMPRESSION:-zstd}"
-if [ "${EXPORT_COMPRESSION}" = "uncompressed" ]; then
-    export_args=(--output "type=image,name={{IMAGE}},compression=uncompressed")
-else
-    export_args=(--output "type=image,name={{IMAGE}},compression=${EXPORT_COMPRESSION},compression-level=3,force-compression=true")
-fi
-
-docker_build() {
-    # $1 = image name; remaining args passed through to docker build.
-    local image="$1"
-    shift
-    local out=("${export_args[@]/'{{IMAGE}}'/${image}}")
-    docker build "${out[@]}" "$@" -f docker/Dockerfile.xpu .
-}
-
-build_vllm_base() (
-    local vllm_source_dir
-    vllm_source_dir=$(mktemp -d)
-    trap 'rm -rf "${vllm_source_dir}"' EXIT
-
-    git clone --depth 1 --branch "${VLLM_VERSION}" \
-        https://github.com/vllm-project/vllm "${vllm_source_dir}"
-
-    local out=("${export_args[@]/'{{IMAGE}}'/${base_image_name}}")
-    docker build "${out[@]}" \
-        --target vllm-openai \
-        -f "${vllm_source_dir}/docker/Dockerfile.xpu" \
-        "${vllm_source_dir}"
-)
-
-if [ -z "$(docker images -q "${base_image_name}")" ]; then
-    build_vllm_base
-fi
-
-# Try building the docker image
-docker_build "${image_name}" --build-arg "VLLM_BASE=${base_image_name}" --build-arg "VLLM_VERSION=${VLLM_VERSION}"
-
-# Setup cleanup
-remove_docker_container() {
-    docker rm -f "${container_name}" || true
-    docker image rm -f "${image_name}" || true
-    docker system prune -f || true
-}
-trap remove_docker_container EXIT
-
-HF_CACHE="${HF_CACHE:-$(realpath ~)/.cache/huggingface}"
-mkdir -p "${HF_CACHE}"
-HF_MOUNT="/root/.cache/huggingface"
-
-time timeout -k 30 30m docker run \
-    --device /dev/dri:/dev/dri \
-    --net=host \
-    --ipc=host \
-    -v /dev/dri/by-path:/dev/dri/by-path \
-    -v "${HF_CACHE}:${HF_MOUNT}" \
-    --security-opt seccomp=unconfined \
-    --entrypoint="" \
-    -e VLLM_LOGGING_LEVEL \
-    -e VLLM_OMNI_LOGGING_LEVEL \
-    -e HF_TOKEN \
-    -e ZE_AFFINITY_MASK \
-    --name "${container_name}" \
-    "${image_name}" \
-    bash -c '
-    set -e
-    echo $ZE_AFFINITY_MASK
-    pip install tblib==3.1.0
-    cd /workspace/vllm-omni
-    pytest -v -s -m "core_model and xpu and B60"
-    pytest -v -s tests/diffusion/quantization/test_mxfp8_config.py
-    pytest -v -s -m "advanced_model and xpu and B60"
-    pytest -v -s -m "omni and xpu and B60"
-'

.buildkite/npu/bootstrap-upload-steps.yml

@@ -1,181 +0,0 @@
-# Uploaded by upload_pipeline.py --upload (not the Buildkite hook).
-# ``if`` is injected by step ``key`` from skip-ci at upload time.
-steps:
-  - label: ":buildkit: Build and Push NPU Test Image - A2"
-    key: image-build-a2
-    agents:
-      queue: "ascend-a2b3"
-      resource_class: "npu-1"
-    plugins:
-      - kubernetes:
-          metadata:
-            annotations:
-              vault.hashicorp.com/agent-init-first: "true"
-              vault.hashicorp.com/agent-inject: "true"
-              vault.hashicorp.com/agent-inject-perms-ca.pem: "0400"
-              vault.hashicorp.com/agent-inject-perms-cert.pem: "0400"
-              vault.hashicorp.com/agent-inject-perms-config.json: "0400"
-              vault.hashicorp.com/agent-inject-perms-key.pem: "0400"
-              vault.hashicorp.com/agent-inject-secret-ca.pem: internal/data/ascend/buildkitd
-              vault.hashicorp.com/agent-inject-secret-cert.pem: internal/data/ascend/buildkitd
-              vault.hashicorp.com/agent-inject-secret-config.json: internal/data/ascend/buildkitd
-              vault.hashicorp.com/agent-inject-secret-key.pem: internal/data/ascend/buildkitd
-              vault.hashicorp.com/agent-inject-template-ca.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.RootCA }}\n{{- end }}"
-              vault.hashicorp.com/agent-inject-template-cert.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.ClientCaCert }}\n{{- end }}"
-              vault.hashicorp.com/agent-inject-template-config.json: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.dockerConfig }}\n{{- end }}"
-              vault.hashicorp.com/agent-inject-template-key.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.ClientCaKey }}\n{{- end }}"
-              vault.hashicorp.com/agent-pre-populate-only: "true"
-              vault.hashicorp.com/agent-run-as-group: "1000"
-              vault.hashicorp.com/agent-run-as-user: "1000"
-              vault.hashicorp.com/agent-service-account-token-volume-name: token-vol
-              vault.hashicorp.com/role: ascend-gha-runners
-              vault.hashicorp.com/secret-volume-path: /home/user/.docker/
-              vault.hashicorp.com/tls-skip-verify: "true"
-          podSpecPatch:
-            volumes:
-            - name: token-vol
-              projected:
-                defaultMode: 420
-                sources:
-                - serviceAccountToken:
-                    audience: api
-                    expirationSeconds: 600
-                    path: token
-    env:
-      VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}"
-      IMAGE_NAME: "vllm-omni-ci-npu"
-      IMAGE_REGISTRY: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry"
-      BUILDKITD_ADDR: "tcp://buildkitd-service.buildkitd:1234"
-    command: |
-      set -ex
-
-      echo "--- Building and pushing NPU Test Image"
-      echo "Image: $${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
-      echo "buildkitd address: $${BUILDKITD_ADDR}"
-
-      if ! command -v buildctl &> /dev/null; then
-        echo "Installing buildctl..."
-        mkdir -p /tmp/buildkit
-        BUILDKIT_VERSION="v0.29.0"
-        wget -q "https://github.com/moby/buildkit/releases/download/$${BUILDKIT_VERSION}/buildkit-$${BUILDKIT_VERSION}.linux-arm64.tar.gz" -O /tmp/buildkit.tar.gz
-        tar -xzf /tmp/buildkit.tar.gz -C /tmp/buildkit
-        cp /tmp/buildkit/bin/buildctl /usr/local/bin/
-      fi
-
-      export DOCKER_CONFIG=/home/user/.docker
-      buildctl \
-        --addr="$${BUILDKITD_ADDR}" \
-        --tlscacert=/home/user/.docker/ca.pem \
-        --tlscert=/home/user/.docker/cert.pem \
-        --tlskey=/home/user/.docker/key.pem \
-        build \
-        --frontend dockerfile.v0 \
-        --local context=. \
-        --local dockerfile=./docker \
-        --opt filename=Dockerfile.npu.ci \
-        --secret id=dockerconfig,src=/home/user/.docker/config.json \
-        --output type=image,name=$${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG},push=true \
-        --progress=plain
-
-      echo "--- Image pushed successfully"
-      echo "$${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
-
-  - label: ":buildkit: Build and Push NPU Test Image - A3"
-    key: image-build-a3
-    agents:
-      queue: "ascend-a2b3"
-      resource_class: "npu-1"
-    plugins:
-      - kubernetes:
-          metadata:
-            annotations:
-              vault.hashicorp.com/agent-init-first: "true"
-              vault.hashicorp.com/agent-inject: "true"
-              vault.hashicorp.com/agent-inject-perms-ca.pem: "0400"
-              vault.hashicorp.com/agent-inject-perms-cert.pem: "0400"
-              vault.hashicorp.com/agent-inject-perms-config.json: "0400"
-              vault.hashicorp.com/agent-inject-perms-key.pem: "0400"
-              vault.hashicorp.com/agent-inject-secret-ca.pem: internal/data/ascend/buildkitd
-              vault.hashicorp.com/agent-inject-secret-cert.pem: internal/data/ascend/buildkitd
-              vault.hashicorp.com/agent-inject-secret-config.json: internal/data/ascend/buildkitd
-              vault.hashicorp.com/agent-inject-secret-key.pem: internal/data/ascend/buildkitd
-              vault.hashicorp.com/agent-inject-template-ca.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.RootCA }}\n{{- end }}"
-              vault.hashicorp.com/agent-inject-template-cert.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.ClientCaCert }}\n{{- end }}"
-              vault.hashicorp.com/agent-inject-template-config.json: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.dockerConfig }}\n{{- end }}"
-              vault.hashicorp.com/agent-inject-template-key.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.ClientCaKey }}\n{{- end }}"
-              vault.hashicorp.com/agent-pre-populate-only: "true"
-              vault.hashicorp.com/agent-run-as-group: "1000"
-              vault.hashicorp.com/agent-run-as-user: "1000"
-              vault.hashicorp.com/agent-service-account-token-volume-name: token-vol
-              vault.hashicorp.com/role: ascend-gha-runners
-              vault.hashicorp.com/secret-volume-path: /home/user/.docker/
-              vault.hashicorp.com/tls-skip-verify: "true"
-          podSpecPatch:
-            volumes:
-            - name: token-vol
-              projected:
-                defaultMode: 420
-                sources:
-                - serviceAccountToken:
-                    audience: api
-                    expirationSeconds: 600
-                    path: token
-    env:
-      VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}-a3"
-      IMAGE_NAME: "vllm-omni-ci-npu"
-      IMAGE_REGISTRY: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry"
-      BUILDKITD_ADDR: "tcp://buildkitd-service.buildkitd:1234"
-    command: |
-      set -ex
-
-      echo "--- Building and pushing NPU Test Image"
-      echo "Image: $${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
-      echo "buildkitd address: $${BUILDKITD_ADDR}"
-
-      if ! command -v buildctl &> /dev/null; then
-        echo "Installing buildctl..."
-        mkdir -p /tmp/buildkit
-        BUILDKIT_VERSION="v0.29.0"
-        wget -q "https://github.com/moby/buildkit/releases/download/$${BUILDKIT_VERSION}/buildkit-$${BUILDKIT_VERSION}.linux-arm64.tar.gz" -O /tmp/buildkit.tar.gz
-        tar -xzf /tmp/buildkit.tar.gz -C /tmp/buildkit
-        cp /tmp/buildkit/bin/buildctl /usr/local/bin/
-      fi
-
-      export DOCKER_CONFIG=/home/user/.docker
-      buildctl \
-        --addr="$${BUILDKITD_ADDR}" \
-        --tlscacert=/home/user/.docker/ca.pem \
-        --tlscert=/home/user/.docker/cert.pem \
-        --tlskey=/home/user/.docker/key.pem \
-        build \
-        --frontend dockerfile.v0 \
-        --local context=. \
-        --local dockerfile=./docker \
-        --opt filename=Dockerfile.npu.ci.a3 \
-        --secret id=dockerconfig,src=/home/user/.docker/config.json \
-        --output type=image,name=$${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG},push=true \
-        --progress=plain
-
-      echo "--- Image pushed successfully"
-      echo "$${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
-
-  - label: "Upload Ready Pipeline"
-    depends_on:
-      - image-build-a2
-      - image-build-a3
-    key: upload-ready-pipeline
-    agents:
-      queue: "cpu_queue_premerge"
-    command: |
-      python3 .buildkite/common/scripts/upload_pipeline.py --upload .buildkite/npu/test-npu-ready.yml
-
-  # L4 Test — main+NIGHTLY=1 (scheduled), or PR with specific label (e.g. add label then Rebuild)
-  - label: "Upload Nightly Pipeline"
-    depends_on:
-      - image-build-a2
-      - image-build-a3
-    key: upload-nightly-pipeline
-    commands:
-      - python3 .buildkite/common/scripts/upload_pipeline.py --upload .buildkite/npu/test-npu-nightly.yml
-    agents:
-      queue: "cpu_queue_premerge"

.buildkite/npu/pipeline-npu.yml

@@ -1,9 +0,0 @@
-# Hook uploads this entry YAML; upload_pipeline.py --upload reads bootstrap-upload-steps.yml
-# and injects ``if`` by step ``key`` from skip-ci.
-steps:
-  - label: ":github: Resolve skip-ci & upload pipeline"
-    key: upload-ci-pipeline
-    commands:
-      - "python3 .buildkite/common/scripts/upload_pipeline.py --upload .buildkite/npu/bootstrap-upload-steps.yml"
-    agents:
-      queue: "cpu_queue_premerge"

.buildkite/npu/test-npu-nightly.yml

@@ -1,233 +0,0 @@
-steps:
-  - group: ":card_index_dividers: Omni Model Test"
-    key: nightly-omni-test-group
-    depends_on: upload-nightly-pipeline
-    if: >-
-      build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test" ||
-      build.pull_request.labels includes "omni-test"
-    steps:
-      - label: ":full_moon: Omni · Perf Test · No Async Chunk"
-        key: nightly-omni-performance-no-async-chunk
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_4
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py -m npu --test-config-file tests/dfx/perf/tests/test_qwen3_omni_no_async_chunk.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-      - label: ":full_moon: Omni · Perf Test · Async Chunk"
-        key: nightly-omni-performance-async-chunk
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_4
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py -m npu --test-config-file tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 Test"
-        mirror_hardwares: a3_npu_2
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-        commands:
-          - pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5_expansion.py -m 'full_model' --run-level 'full_model'
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 · Duplex Test"
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_2
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-        commands:
-          - >-
-            pytest -s -v
-            tests/e2e/online_serving/test_minicpmo_4_5_duplex.py
-            tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
-            -m "npu and A3 and omni"
-            --run-level full_model
-      - label: ":full_moon: Omni · MiniCPM-o 4.5 · Accuracy Test"
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_2
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-        commands:
-          - |
-            set +e
-            pytest -s -v tests/e2e/accuracy/minicpmo_4_5/test_minicpmo_4_5.py -m "full_model and npu and A3" --run-level full_model
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/e2e/accuracy/minicpmo_4_5/results/*.json"
-            exit $$EXIT
-  - group: ":card_index_dividers: TTS Model Test"
-    key: nightly-tts-test-group
-    depends_on: upload-nightly-pipeline
-    if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test" || build.pull_request.labels includes "tts-test"
-    steps:
-      - label: ":full_moon: TTS · Perf Test"
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_2
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py -m npu --test-config-file tests/dfx/perf/tests/test_tts.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
-            exit $$EXIT
-  - group: ":card_index_dividers: Diffusion X2I(&A&T) Model Test"
-    key: nightly-diffusion-x2iat-group
-    depends_on: upload-nightly-pipeline
-    if: >-
-      build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test" ||
-      build.pull_request.labels includes "diffusion-x2iat-test"
-    steps:
-      - label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image-Edit-2511"
-        key: nightly-diffusion-x2iat-performance-qwen-image-edit-2511
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_8
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-          DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - export CACHE_DIT_VERSION=1.5.0
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m npu --test-config-file tests/dfx/perf/tests/test_qwen_image_edit_2511_vllm_omni.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT
-  - group: ":card_index_dividers: Diffusion I2I Model Test"
-    key: nightly-HunyuanImage3-x2i-test-group
-    depends_on: upload-nightly-pipeline
-    if: >-
-      build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test" ||
-      build.pull_request.labels includes "diffusion-x2iat-test"
-    steps:
-      - label: ":full_moon: HunyuanImage3-DIT · Accuracy Test"
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_4
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          HUNYUAN_IMAGE3_MODEL: "tencent/HunyuanImage-3.0-Instruct"
-          HUNYUAN_IMAGE3_DEVICES: "0,1,2,3"
-          DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
-        commands:
-          - pytest -s -v tests/e2e/accuracy/test_hunyuan_image3_pixel_accuracy.py -m "full_model and A3" --run-level full_model
-  - group: ":card_index_dividers: Diffusion Benchmark Perf Test"
-    key: nightly-diffusion-benchmark-group
-    depends_on: upload-nightly-pipeline
-    if: >-
-      build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test" ||
-      build.pull_request.labels includes "diffusion-x2iat-test"
-    steps:
-      - label: ":full_moon: Diffusion Perf · HunyuanImage3 TP=2 CFGP=2"
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_4
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          HF_TOKEN: "${HF_TOKEN}"
-          DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m A3 --test-config-file tests/dfx/perf/tests/test_hunyuan_image_tp2_cfgp2.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT
-      - label: ":full_moon: Diffusion Perf · HunyuanImage3 TP=2 SP=2"
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_4
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          HF_TOKEN: "${HF_TOKEN}"
-          DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m A3 --test-config-file tests/dfx/perf/tests/test_hunyuan_image_tp2_sp2.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT
-      - label: ":full_moon: Diffusion Perf · HunyuanImage3 TP=4"
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_4
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          HF_TOKEN: "${HF_TOKEN}"
-          DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m A3 --test-config-file tests/dfx/perf/tests/test_hunyuan_image_tp4.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT
-  - group: ":card_index_dividers: Diffusion X2V Model Test"
-    key: nightly-diffusion-x2v-group
-    depends_on: upload-nightly-pipeline
-    if: >-
-      build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test" ||
-      build.pull_request.labels includes "diffusion-x2v-test"
-    steps:
-      - label: ":full_moon: Diffusion X2V · Function Test"
-        mirror_hardwares: a2b3_npu_4
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k npu_i2v --run-level "full_model"
-      - label: ":full_moon: Diffusion X2V · Perf Test"
-        key: nightly-diffusion-x2v-performance
-        timeout_in_minutes: 180
-        mirror_hardwares: a3_npu_4
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-          DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
-        commands:
-          - export DIFFUSION_BENCHMARK_DIR=tests/dfx/perf/results
-          - |
-            set +e
-            pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py -m npu --test-config-file tests/dfx/perf/tests/test_wan22_i2v_vllm_omni.json
-            EXIT=$$?
-            buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
-            buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
-            exit $$EXIT

.buildkite/npu/test-npu-ready.yml

@@ -1,41 +0,0 @@
-steps:
-  - group: ":card_index_dividers: Omni Model Test"
-    key: ready-omni-group
-    depends_on: upload-ready-pipeline
-    steps:
-      - label: "Omni · MiniCPM-o 4.5 Test"
-        mirror_hardwares: a3_npu_2
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-        commands:
-          - pytest -s -v tests/e2e/offline_inference/test_minicpmo_4_5.py tests/e2e/online_serving/test_minicpmo_4_5.py -m 'core_model and npu and A3 and omni' --run-level 'core_model'
-      - label: "Omni · MiniCPM-o 4.5 Duplex Test"
-        mirror_hardwares: a3_npu_2
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_minicpmo_4_5_duplex.py -m 'core_model and npu and A3 and omni' --run-level 'core_model'
-      - label: "Omni · MiniCPM-o 4.5 Perf Test"
-        timeout_in_minutes: 60
-        mirror_hardwares: a3_npu_2
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-        commands:
-          - export BENCHMARK_DIR=tests/dfx/perf/results
-          - pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_minicpmo_4_5_ready.json -m 'core_model and npu and A3 and omni'
-
-  - group: ":card_index_dividers: TTS Model Test"
-    key: ready-tts-group
-    depends_on: upload-ready-pipeline
-    steps:
-      - label: ":sound: TTS · Qwen3-TTS CustomVoice Test"
-        mirror_hardwares: a2b3_npu_1
-        env:
-          VLLM_WORKER_MULTIPROC_METHOD: spawn
-          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
-          HF_TOKEN: "${HF_TOKEN}"
-        commands:
-          - pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m 'core_model and npu' --run-level 'core_model'

.buildkite/pipeline-intel.yaml

@@ -1,16 +1,16 @@
-# .buildkite/intel/pipeline-intel.yml
+# .buildkite/pipeline-intel.yaml
 steps:
   - group: "INTEL Tests"
     steps:
       - label: "Intel: XPU Test"
-        command: "bash .buildkite/intel/scripts/run-xpu-test.sh"
+        command: "bash .buildkite/scripts/hardware_ci/run-xpu-test.sh"
         agents:
           queue: "intel-gpu-omni"
         env:
           DOCKER_BUILDKIT: "1"
           # Buildkite will automatically replace this with the actual commit hash
           VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}"
-          VLLM_VERSION: "v0.27.0"
+          VLLM_VERSION: "v0.21.0"
         priority: 100
         timeout_in_minutes: 60
         soft_fail: false

.buildkite/pipeline-npu-a3.yaml

@@ -88,7 +88,7 @@
 #   #     queue: "ascend-a3"
 #   #     resource_class: "npu-2"
 #   #   command: |
-#   #     buildkite-agent pipeline upload .buildkite/npu/test-npu-ready.yml
+#   #     buildkite-agent pipeline upload .buildkite/test-npu-ready.yaml
 
   # # L4 Test — main+NIGHTLY=1 (scheduled), or PR with specific label (e.g. add label then Rebuild)
   # - label: "Upload Nightly Pipeline"
@@ -104,7 +104,7 @@
   #       build.pull_request.labels includes "diffusion-x2v-test"
   #     ))
   #   commands:
-  #     - buildkite-agent pipeline upload .buildkite/npu/test-npu-nightly.yml
+  #     - buildkite-agent pipeline upload .buildkite/test-npu-nightly.yaml
   #   agents:
   #     queue: "ascend-a3"
   #     resource_class: "npu-2"

.buildkite/pipeline-npu.yaml

@@ -0,0 +1,112 @@
+steps:
+  - label: ":buildkit: Build and Push NPU Test Image - A2"
+    key: image-build
+    agents:
+      queue: "ascend-a2b3"
+      resource_class: "npu-1"
+    plugins:
+      - kubernetes:
+          metadata:
+            annotations:
+              vault.hashicorp.com/agent-init-first: "true"
+              vault.hashicorp.com/agent-inject: "true"
+              vault.hashicorp.com/agent-inject-perms-ca.pem: "0400"
+              vault.hashicorp.com/agent-inject-perms-cert.pem: "0400"
+              vault.hashicorp.com/agent-inject-perms-config.json: "0400"
+              vault.hashicorp.com/agent-inject-perms-key.pem: "0400"
+              vault.hashicorp.com/agent-inject-secret-ca.pem: internal/data/ascend/buildkitd
+              vault.hashicorp.com/agent-inject-secret-cert.pem: internal/data/ascend/buildkitd
+              vault.hashicorp.com/agent-inject-secret-config.json: internal/data/ascend/buildkitd
+              vault.hashicorp.com/agent-inject-secret-key.pem: internal/data/ascend/buildkitd
+              vault.hashicorp.com/agent-inject-template-ca.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.RootCA }}\n{{- end }}"
+              vault.hashicorp.com/agent-inject-template-cert.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.ClientCaCert }}\n{{- end }}"
+              vault.hashicorp.com/agent-inject-template-config.json: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.dockerConfig }}\n{{- end }}"
+              vault.hashicorp.com/agent-inject-template-key.pem: "{{- with secret \"internal/data/ascend/buildkitd\" -}}\n{{ .Data.data.ClientCaKey }}\n{{- end }}"
+              vault.hashicorp.com/agent-pre-populate-only: "true"
+              vault.hashicorp.com/agent-run-as-group: "1000"
+              vault.hashicorp.com/agent-run-as-user: "1000"
+              vault.hashicorp.com/agent-service-account-token-volume-name: token-vol
+              vault.hashicorp.com/role: ascend-gha-runners
+              vault.hashicorp.com/secret-volume-path: /home/user/.docker/
+              vault.hashicorp.com/tls-skip-verify: "true"
+          podSpecPatch:
+            volumes:
+            - name: token-vol
+              projected:
+                defaultMode: 420
+                sources:
+                - serviceAccountToken:
+                    audience: api
+                    expirationSeconds: 600
+                    path: token
+    env:
+      VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}"
+      IMAGE_NAME: "vllm-omni-ci-npu"
+      IMAGE_REGISTRY: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry"
+      BUILDKITD_ADDR: "tcp://buildkitd-service.buildkitd:1234"
+    command: |
+      set -ex
+
+      echo "--- Building and pushing NPU Test Image"
+      echo "Image: $${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
+      echo "buildkitd address: $${BUILDKITD_ADDR}"
+
+      if ! command -v buildctl &> /dev/null; then
+        echo "Installing buildctl..."
+        mkdir -p /tmp/buildkit
+        BUILDKIT_VERSION="v0.29.0"
+        wget -q "https://github.com/moby/buildkit/releases/download/$${BUILDKIT_VERSION}/buildkit-$${BUILDKIT_VERSION}.linux-arm64.tar.gz" -O /tmp/buildkit.tar.gz
+        tar -xzf /tmp/buildkit.tar.gz -C /tmp/buildkit
+        cp /tmp/buildkit/bin/buildctl /usr/local/bin/
+      fi
+
+      export DOCKER_CONFIG=/home/user/.docker
+      buildctl \
+        --addr="$${BUILDKITD_ADDR}" \
+        --tlscacert=/home/user/.docker/ca.pem \
+        --tlscert=/home/user/.docker/cert.pem \
+        --tlskey=/home/user/.docker/key.pem \
+        build \
+        --frontend dockerfile.v0 \
+        --local context=. \
+        --local dockerfile=./docker \
+        --opt filename=Dockerfile.npu.ci \
+        --secret id=dockerconfig,src=/home/user/.docker/config.json \
+        --output type=image,name=$${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG},push=true \
+        --progress=plain
+
+      echo "--- Image pushed successfully"
+      echo "$${IMAGE_REGISTRY}/$${IMAGE_NAME}:$${VLLM_IMAGE_TAG}"
+
+  - label: "Upload Ready Pipeline"
+    depends_on: image-build
+    key: upload-ready-pipeline
+    if: >-
+      build.branch != "main" && (
+        build.pull_request.labels includes "npu-test" ||
+        build.pull_request.labels includes "ready"
+      )
+    agents:
+      queue: "ascend-a2b3"
+      resource_class: "npu-1"
+    command: |
+      buildkite-agent pipeline upload .buildkite/test-npu-ready.yaml
+
+  # L4 Test — main+NIGHTLY=1 (scheduled), or PR with specific label (e.g. add label then Rebuild)
+  - label: "Upload Nightly Pipeline"
+    depends_on: image-build
+    key: upload-nightly-pipeline
+    if: >-
+      (build.branch == "main" && build.env("NIGHTLY") == "1") ||
+      (build.branch != "main" && (
+        build.pull_request.labels includes "nightly-test" ||
+        build.pull_request.labels includes "omni-test" ||
+        build.pull_request.labels includes "tts-test" ||
+        build.pull_request.labels includes "diffusion-x2iat-test" ||
+        build.pull_request.labels includes "diffusion-x2v-test"
+      ))
+    commands:
+      - buildkite-agent pipeline upload .buildkite/test-npu-nightly.yaml
+    agents:
+      queue: "ascend-a2b3"
+      resource_class: "npu-1"

.buildkite/pipeline.yml

@@ -0,0 +1,76 @@
+# Document 1: Buildkite loads only this block on first parse. The next step resolves docs-only skip-ci
+# from git diff, then uploads document 2. When docs-only skip applies, image-build still runs for the nightly
+# exception in upload_pipeline_with_skip_ci.sh (nightly-test label or main NIGHTLY=1); otherwise upload-nightly
+# can be skipped together with test-ready/test-merge. Weekly uploads also depend on image-build.
+
+# Document 2: appended after `---`; same file, read by upload_pipeline_with_skip_ci.sh (not evaluated as a second pipeline by Buildkite). Child uploads include test-ready.yml, test-merge.yml, test-nightly.yml, and test-weekly.yml.
+steps:
+  - label: ":github: Resolve skip-ci & upload pipeline"
+    key: upload-ci-pipeline
+    commands:
+      - "bash .buildkite/scripts/upload_pipeline_with_skip_ci.sh"
+    agents:
+      queue: "cpu_queue_premerge"
+
+---
+steps:
+  - label: ":docker: Build image"
+    key: image-build
+    if: __IMAGE_BUILD_IF__
+    commands:
+      - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
+      - "docker build --progress=plain --file docker/Dockerfile.ci -t vllm-omni-ci ."
+      - "docker tag vllm-omni-ci public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT"
+      - "docker push public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT"
+    agents:
+      queue: "cpu_queue_premerge"
+
+  # L2 Test
+  - label: "Upload Ready Pipeline"
+    depends_on: image-build
+    key: upload-ready-pipeline
+    if: __UPLOAD_READY_IF__
+    commands:
+      - buildkite-agent pipeline upload .buildkite/test-ready.yml
+    agents:
+      queue: "cpu_queue_premerge"
+
+  # L3 Test
+  - label: "Upload Merge Pipeline"
+    depends_on: image-build
+    key: upload-merge-pipeline
+    if: __UPLOAD_MERGE_IF__
+    commands:
+      - buildkite-agent pipeline upload .buildkite/test-merge.yml
+    agents:
+      queue: "cpu_queue_premerge"
+
+  # L4 Test — main+NIGHTLY=1 (scheduled), or PR with specific label (e.g. add label then Rebuild)
+  - label: "Upload Nightly Pipeline"
+    depends_on: image-build
+    key: upload-nightly-pipeline
+    if: >-
+      (build.branch == "main" && build.env("NIGHTLY") == "1") ||
+      (build.branch != "main" && (
+        build.pull_request.labels includes "nightly-test" ||
+        build.pull_request.labels includes "omni-test" ||
+        build.pull_request.labels includes "tts-test" ||
+        build.pull_request.labels includes "diffusion-x2iat-test" ||
+        build.pull_request.labels includes "diffusion-x2v-test"
+      ))
+    commands:
+      - buildkite-agent pipeline upload .buildkite/test-nightly.yml
+    agents:
+      queue: "cpu_queue_premerge"
+
+  # L5 Test — main+WEEKLY=1 (scheduled), or PR with weekly-test label
+  - label: "Upload Weekly Pipeline"
+    depends_on: image-build
+    key: upload-weekly-pipeline
+    if: >-
+      (build.branch == "main" && build.env("WEEKLY") == "1") ||
+      (build.branch != "main" && build.pull_request.labels includes "weekly-test")
+    commands:
+      - buildkite-agent pipeline upload .buildkite/test-weekly.yml
+    agents:
+      queue: "cpu_queue_premerge"

.buildkite/rebase-pipeline.yaml

@@ -2,7 +2,10 @@ steps:
   - label: ":docker: Build image"
     key: image-build
     commands:
-      - "bash .buildkite/cuda/scripts/build-ci-image.sh"
+      - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
+      - "docker build --progress=plain --file docker/Dockerfile.ci -t vllm-omni-ci ."
+      - "docker tag vllm-omni-ci public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT"
+      - "docker push public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT"
     agents:
       queue: "cpu_queue_premerge"
 
@@ -11,7 +14,7 @@ steps:
     depends_on: image-build
     key: upload-ready-pipeline
     commands:
-      - python3 .buildkite/common/scripts/upload_pipeline.py --upload --all .buildkite/cuda/test-ready.yml
+      - buildkite-agent pipeline upload .buildkite/test-ready.yml
     agents:
       queue: "cpu_queue_premerge"
 
@@ -20,7 +23,7 @@ steps:
     depends_on: image-build
     key: upload-merge-pipeline
     commands:
-      - python3 .buildkite/common/scripts/upload_pipeline.py --upload --all .buildkite/cuda/test-merge.yml
+      - buildkite-agent pipeline upload .buildkite/test-merge.yml
     agents:
       queue: "cpu_queue_premerge"
 
@@ -30,6 +33,6 @@ steps:
     key: upload-nightly-pipeline
     if: build.env("NIGHTLY") == "1"
     commands:
-      - python3 .buildkite/common/scripts/upload_pipeline.py --upload --all .buildkite/cuda/test-nightly.yml
+      - buildkite-agent pipeline upload .buildkite/test-nightly.yml
     agents:
       queue: "cpu_queue_premerge"

.buildkite/release-pipeline.yaml

@@ -16,7 +16,7 @@ steps:
       - "uv venv --python=3.12 && source .venv/bin/activate"
       - "uv pip install --upgrade build"
       - "python3 -m build"
-      - "bash .buildkite/release/scripts/upload-nightly-wheels.sh"
+      - "bash .buildkite/scripts/upload-nightly-wheels.sh"
 
   - label: "Generate and upload wheel indices"
     depends_on: "build-wheel"
@@ -24,7 +24,7 @@ steps:
     agents:
       queue: small_cpu_queue_release
     commands:
-      - "bash .buildkite/release/scripts/generate-and-upload-nightly-index.sh"
+      - "bash .buildkite/scripts/generate-and-upload-nightly-index.sh"
 
   - block: "Upload release wheels to PyPI"
     depends_on: "build-wheel"
@@ -38,13 +38,11 @@ steps:
     agents:
       queue: small_cpu_queue_release
     commands:
-      - "bash .buildkite/release/scripts/publish-release-wheels-pypi.sh"
+      - "bash .buildkite/scripts/publish-release-wheels-pypi.sh"
 
-  # Auto-skip when NIGHTLY=1 (scheduled); otherwise require manual unblock.
   - block: "Unblock to build release Docker images"
     depends_on: ~
     key: block-build-release-images
-    if: build.env("NIGHTLY") != "1"
 
   - group: "Build release Docker images"
     key: "build-release-images"
@@ -65,7 +63,7 @@ steps:
               --progress plain \
               -f docker/Dockerfile.cuda .
           - "docker push public.ecr.aws/q9t5s3a7/vllm-omni-release-repo:$BUILDKITE_COMMIT-$(uname -m)"
-          # Fallback default tag (no arch suffix) if arm64 build fails.
+          # re-tag to default image tag and push, just in case arm64 build fails
           - "docker tag public.ecr.aws/q9t5s3a7/vllm-omni-release-repo:$BUILDKITE_COMMIT-$(uname -m) public.ecr.aws/q9t5s3a7/vllm-omni-release-repo:$BUILDKITE_COMMIT"
           - "docker push public.ecr.aws/q9t5s3a7/vllm-omni-release-repo:$BUILDKITE_COMMIT"
         env:
@@ -88,26 +86,6 @@ steps:
         env:
           DOCKER_BUILDKIT: "1"
 
-  # NIGHTLY=1 only: promote ECR images to DockerHub nightly tags, then prune.
-  - label: "Publish nightly multi-arch image to DockerHub"
-    depends_on:
-      - build-release-image-x86
-      - build-release-image-arm64
-    if: build.env("NIGHTLY") == "1"
-    key: publish-nightly-images-dockerhub
-    agents:
-      queue: small_cpu_queue_release
-    commands:
-      - "bash .buildkite/release/scripts/publish-release-images.sh nightly"
-      - "bash .buildkite/release/scripts/cleanup-nightly-builds.sh"
-    plugins:
-      - docker-login#v3.0.0:
-          username: vllmbot
-          password-env: DOCKERHUB_TOKEN
-    env:
-      DOCKER_BUILDKIT: "1"
-      DOCKERHUB_USERNAME: "vllmbot"
-
   - block: "Publish release images to DockerHub"
     key: block-publish-release-images
     depends_on:
@@ -122,7 +100,7 @@ steps:
     agents:
       queue: small_cpu_queue_release
     commands:
-      - "bash .buildkite/release/scripts/publish-release-images.sh"
+      - "bash .buildkite/scripts/publish-release-images.sh"
     plugins:
       - docker-login#v3.0.0:
           username: vllmbot

.buildkite/release/scripts/cleanup-nightly-builds.sh

@@ -1,147 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: Apache-2.0
-#
-# Clean up old nightly builds from DockerHub (vllm/vllm-omni), keeping the
-# newest 14 tags with the nightly- prefix.
-
-set -ex
-
-TAG_PREFIX="nightly-"
-REPO="vllm/vllm-omni"
-REPO_API_URL="https://hub.docker.com/v2/repositories/${REPO}/tags"
-
-echo "Cleaning up tags with prefix: $TAG_PREFIX in repository: $REPO"
-
-if [ -z "$DOCKERHUB_TOKEN" ]; then
-  echo "Error: DOCKERHUB_TOKEN environment variable is not set"
-  exit 1
-fi
-
-if [ -z "$DOCKERHUB_USERNAME" ]; then
-  echo "Error: DOCKERHUB_USERNAME environment variable is not set"
-  exit 1
-fi
-
-echo "Getting DockerHub bearer token..."
-set +x
-BEARER_TOKEN=$(curl -s -X POST \
-  -H "Content-Type: application/json" \
-  -d "{\"username\": \"$DOCKERHUB_USERNAME\", \"password\": \"$DOCKERHUB_TOKEN\"}" \
-  "https://hub.docker.com/v2/users/login" | jq -r '.token')
-set -x
-
-if [ -z "$BEARER_TOKEN" ] || [ "$BEARER_TOKEN" = "null" ]; then
-  echo "Error: Failed to get DockerHub bearer token"
-  exit 1
-fi
-
-get_all_tags() {
-  local page=1
-  local all_tags=""
-  # Hub `name` is a partial match (not a strict prefix). Use it to narrow the
-  # list, then enforce startswith() client-side. Exhaust API pages; do not
-  # stop merely because a page has no matching tags after filtering.
-  local name_query
-  name_query=$(printf '%s' "$TAG_PREFIX" | jq -sRr @uri)
-
-  while true; do
-    set +x
-    local response
-    response=$(curl -s -H "Authorization: Bearer $BEARER_TOKEN" \
-      "$REPO_API_URL?page=$page&page_size=100&name=${name_query}")
-    set -x
-
-    local page_count
-    page_count=$(echo "$response" | jq -r '.results | length')
-    if [ -z "$page_count" ] || [ "$page_count" = "0" ] || [ "$page_count" = "null" ]; then
-      break
-    fi
-
-    local tags
-    tags=$(echo "$response" | jq -r --arg prefix "$TAG_PREFIX" \
-      '.results[] | select(.name | startswith($prefix)) | "\(.last_updated)|\(.name)"')
-
-    if [ -n "$tags" ]; then
-      all_tags="$all_tags$tags"$'\n'
-    fi
-    page=$((page + 1))
-  done
-
-  echo "$all_tags" | sort -r | cut -d'|' -f2
-}
-
-delete_tag() {
-  local tag_name="$1"
-  echo "Deleting tag: $tag_name"
-
-  local delete_url="https://hub.docker.com/v2/repositories/${REPO}/tags/$tag_name"
-  set +x
-  local response http_code body
-  response=$(curl -s -w "\n%{http_code}" -X DELETE \
-    -H "Authorization: Bearer $BEARER_TOKEN" "$delete_url")
-  set -x
-  http_code=$(printf '%s\n' "$response" | tail -n1)
-  body=$(printf '%s\n' "$response" | sed '$d')
-
-  if [ "$http_code" -ge 200 ] && [ "$http_code" -lt 300 ]; then
-    echo "Successfully deleted tag: $tag_name (HTTP ${http_code})"
-    return 0
-  fi
-
-  local detail=""
-  if echo "$body" | jq -e '.detail' > /dev/null 2>&1; then
-    detail=$(echo "$body" | jq -r '.detail')
-  elif [ -n "$body" ]; then
-    detail="$body"
-  else
-    detail="(empty response body)"
-  fi
-  echo "Error: Failed to delete tag $tag_name (HTTP ${http_code}): ${detail}"
-  return 1
-}
-
-echo "Fetching all tags from DockerHub..."
-all_tags=$(get_all_tags)
-
-if [ -z "$all_tags" ]; then
-  echo "No tags found to clean up"
-  exit 0
-fi
-
-total_tags=$(echo "$all_tags" | wc -l)
-echo "Found $total_tags tags"
-
-tags_to_keep=14
-tags_to_delete=$((total_tags - tags_to_keep))
-
-if [ $tags_to_delete -le 0 ]; then
-  echo "No tags need to be deleted (only $total_tags tags found, keeping $tags_to_keep)"
-  exit 0
-fi
-
-echo "Will delete $tags_to_delete old tags, keeping the newest $tags_to_keep"
-
-tags_to_delete_list=$(echo "$all_tags" | tail -n +$((tags_to_keep + 1)))
-
-if [ -z "$tags_to_delete_list" ]; then
-  echo "No tags to delete"
-  exit 0
-fi
-
-echo "Deleting old tags..."
-delete_failures=0
-while IFS= read -r tag; do
-  if [ -n "$tag" ]; then
-    if ! delete_tag "$tag"; then
-      delete_failures=$((delete_failures + 1))
-    fi
-    sleep 1
-  fi
-done <<< "$tags_to_delete_list"
-
-if [ "$delete_failures" -gt 0 ]; then
-  echo "Cleanup finished with ${delete_failures} deletion failure(s)"
-  exit 1
-fi
-
-echo "Cleanup completed successfully"

.buildkite/release/scripts/publish-release-images.sh

@@ -1,87 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: Apache-2.0
-#
-# Publish Docker images from ECR staging to DockerHub.
-#
-# Usage:
-#   publish-release-images.sh            # release mode (default)
-#   publish-release-images.sh release
-#   publish-release-images.sh nightly
-#
-# Release tags: latest, v<version>
-# Nightly tags: nightly, nightly-<commit>
-
-set -euo pipefail
-
-MODE="${1:-release}"
-
-DOCKERHUB_REPO="vllm/vllm-omni"
-ECR_REPO="public.ecr.aws/q9t5s3a7/vllm-omni-release-repo"
-COMMIT="$BUILDKITE_COMMIT"
-PRIMARY_TAGS=()
-EXTRA_MANIFEST_TAGS=()
-
-case "${MODE}" in
-  release)
-    RELEASE_VERSION=$(buildkite-agent meta-data get release-version --default "" | sed 's/^v//')
-    if [ -z "${RELEASE_VERSION}" ]; then
-      echo "ERROR: release-version metadata not set"
-      exit 1
-    fi
-    PRIMARY_TAGS=("latest" "v${RELEASE_VERSION}")
-    ;;
-  nightly)
-    # Commit-pinned manifest reuses nightly-{x86_64,aarch64} arch images.
-    PRIMARY_TAGS=("nightly")
-    EXTRA_MANIFEST_TAGS=("nightly-${COMMIT}")
-    ;;
-  *)
-    echo "Usage: $0 {release|nightly}"
-    exit 2
-    ;;
-esac
-
-echo "========================================"
-echo "Publishing ${MODE} images to ${DOCKERHUB_REPO}"
-echo "  Commit: ${COMMIT}"
-echo "  Primary tags: ${PRIMARY_TAGS[*]}"
-if [ ${#EXTRA_MANIFEST_TAGS[@]} -gt 0 ]; then
-  echo "  Extra manifests: ${EXTRA_MANIFEST_TAGS[*]}"
-fi
-echo "========================================"
-
-aws ecr-public get-login-password --region us-east-1 | \
-  docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
-
-SRC_X86="${ECR_REPO}:${COMMIT}-x86_64"
-SRC_ARM="${ECR_REPO}:${COMMIT}-aarch64"
-
-docker pull "${SRC_X86}"
-docker pull "${SRC_ARM}"
-
-publish_manifest() {
-  local tag="$1"
-  local arch_tag_base="$2"
-  docker manifest rm "${DOCKERHUB_REPO}:${tag}" || true
-  docker manifest create \
-    "${DOCKERHUB_REPO}:${tag}" \
-    "${DOCKERHUB_REPO}:${arch_tag_base}-x86_64" \
-    "${DOCKERHUB_REPO}:${arch_tag_base}-aarch64"
-  docker manifest push "${DOCKERHUB_REPO}:${tag}"
-}
-
-for tag in "${PRIMARY_TAGS[@]}"; do
-  docker tag "${SRC_X86}" "${DOCKERHUB_REPO}:${tag}-x86_64"
-  docker tag "${SRC_ARM}" "${DOCKERHUB_REPO}:${tag}-aarch64"
-  docker push "${DOCKERHUB_REPO}:${tag}-x86_64"
-  docker push "${DOCKERHUB_REPO}:${tag}-aarch64"
-  publish_manifest "${tag}" "${tag}"
-done
-
-ARCH_BASE="${PRIMARY_TAGS[0]}"
-for tag in "${EXTRA_MANIFEST_TAGS[@]}"; do
-  publish_manifest "${tag}" "${ARCH_BASE}"
-done
-
-echo ""
-echo "Successfully published ${MODE} images"

.buildkite/scripts/docker_login_ecr_public.sh

@@ -0,0 +1,73 @@
+#!/bin/bash
+# Helper function to safely login to ECR Public with per-job config isolation
+# Uses DOCKER_CONFIG environment variable to prevent race conditions
+#
+# This script prevents the "device or resource busy" error by giving each
+# Buildkite job its own isolated Docker config directory.
+#
+# Usage:
+#   source docker_login_ecr_public.sh && safe_docker_login_ecr_public
+
+set -euo pipefail
+
+# Configuration
+ECR_REGISTRY="public.ecr.aws"
+
+setup_isolated_docker_config() {
+    # Use BUILDKITE_JOB_ID for job-specific isolation
+    # Fallback to PID if running outside Buildkite
+    local job_id="${BUILDKITE_JOB_ID:-$$}"
+
+    # Set Docker config to job-specific directory
+    export DOCKER_CONFIG="/tmp/docker-config-${job_id}"
+
+    # Create directory if it doesn't exist
+    mkdir -p "$DOCKER_CONFIG"
+
+    echo "[docker-config] Using isolated Docker config: $DOCKER_CONFIG"
+}
+
+check_docker_auth() {
+    # Check if already authenticated to the given registry
+    # Returns 0 if authenticated, 1 if not
+    local registry="$1"
+
+    # Check if credentials exist in the isolated config
+    if [[ -f "$DOCKER_CONFIG/config.json" ]]; then
+        # Check if registry is present in config
+        if grep -q "$registry" "$DOCKER_CONFIG/config.json" 2>/dev/null; then
+            return 0
+        fi
+    fi
+
+    return 1
+}
+
+safe_docker_login_ecr_public() {
+    # Setup isolated config first
+    setup_isolated_docker_config
+
+    local registry="$ECR_REGISTRY"
+
+    # Check if already authenticated (within this job)
+    if check_docker_auth "$registry"; then
+        echo "[docker-login] Already authenticated to $registry in this job"
+        return 0
+    fi
+
+    # Perform login to isolated config directory
+    echo "[docker-login] Logging in to $ECR_REGISTRY (isolated config)..."
+    if aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$ECR_REGISTRY"; then
+        echo "[docker-login] Login successful (config: $DOCKER_CONFIG)"
+        return 0
+    else
+        local exit_code=$?
+        echo "[docker-login] ERROR: Login failed with exit code $exit_code" >&2
+        return $exit_code
+    fi
+}
+
+# Execute if run as script (not sourced)
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    safe_docker_login_ecr_public
+fi

.buildkite/scripts/generate-and-upload-nightly-index.sh

@@ -36,12 +36,12 @@ mkdir -p "$INDICES_OUTPUT_DIR"
 
 # HACK: we do not need regex module here, but it is required by pre-commit hook
 # To avoid any external dependency, we simply replace it back to the stdlib re module
-sed -i.bak 's/import regex as re/import re/g' .buildkite/release/scripts/generate-nightly-index.py && rm -f .buildkite/release/scripts/generate-nightly-index.py.bak
+sed -i.bak 's/import regex as re/import re/g' .buildkite/scripts/generate-nightly-index.py && rm -f .buildkite/scripts/generate-nightly-index.py.bak
 
 # Generate indices -- the version is just the commit hash (not omni/{commit})
 # because relative paths are computed between the index and wheel directories,
 # both of which live under the omni/ prefix in S3.
-$PYTHON .buildkite/release/scripts/generate-nightly-index.py \
+$PYTHON .buildkite/scripts/generate-nightly-index.py \
     --version "$BUILDKITE_COMMIT" \
     --current-objects "$obj_json" \
     --output-dir "$INDICES_OUTPUT_DIR" \
@@ -78,7 +78,7 @@ if [[ "$version" != *"dev"* ]]; then
     rm -rf "${INDICES_OUTPUT_DIR:?}"
     mkdir -p "$INDICES_OUTPUT_DIR"
     # wheel-dir is overridden to be the commit directory, so that the indices point to the correct wheel path
-    $PYTHON .buildkite/release/scripts/generate-nightly-index.py \
+    $PYTHON .buildkite/scripts/generate-nightly-index.py \
         --version "$s3_version" \
         --wheel-dir "$BUILDKITE_COMMIT" \
         --current-objects "$obj_json" \

.buildkite/scripts/hardware_ci/run-amd-test.sh

@@ -56,7 +56,7 @@ container_name="rocm_${BUILDKITE_COMMIT}_$(tr -dc A-Za-z0-9 < /dev/urandom | hea
 # # Install AWS CLI to authenticate to ECR Public Gallery to get higher rate limit for pulling images
 # sudo apt-get update && sudo apt-get install -y awscli
 ##  Use safe docker login helper to prevent race conditions
-# source "$(dirname "${BASH_SOURCE[0]}")/../../common/scripts/docker_login_ecr_public.sh"
+# source "$(dirname "${BASH_SOURCE[0]}")/../docker_login_ecr_public.sh"
 # safe_docker_login_ecr_public
 
 ## Pull the container from AMD Docker Hub
@@ -64,8 +64,7 @@ container_name="rocm_${BUILDKITE_COMMIT}_$(tr -dc A-Za-z0-9 < /dev/urandom | hea
 docker pull "${image_name}"
 
 remove_docker_container() {
-   docker ps -aq --filter "name=${container_name}" | xargs -r docker rm -f || true
+   docker rm -f "${container_name}" || docker image rm -f "${image_name}" || true
-   docker image rm -f "${image_name}" || true
 }
 trap remove_docker_container EXIT
 
@@ -108,6 +107,7 @@ if [[ $commands == *"--shard-id="* ]]; then
         --network=host \
         --shm-size=16gb \
         --group-add "$render_gid" \
+        --rm \
         -e MIOPEN_DEBUG_CONV_DIRECT=0 \
         -e MIOPEN_DEBUG_CONV_GEMM=0 \
         -e VLLM_ROCM_USE_AITER=0 \
@@ -140,6 +140,7 @@ else
           --network=host \
           --shm-size=16gb \
           --group-add "$render_gid" \
+          --rm \
           -e MIOPEN_DEBUG_CONV_DIRECT=0 \
           -e MIOPEN_DEBUG_CONV_GEMM=0 \
           -e VLLM_ROCM_USE_AITER=0 \

.buildkite/scripts/hardware_ci/run-xpu-test.sh

@@ -0,0 +1,57 @@
+#!/bin/bash
+
+# This script build the XPU docker image and run the offline inference inside the container.
+set -ex
+
+omni_source_dir=$(git rev-parse --show-toplevel)
+
+base_image_name="xpu/vllm-omni-ci-base:${VLLM_VERSION:?VLLM_VERSION must be set}"
+image_name="xpu/vllm-omni-ci:${BUILDKITE_COMMIT:?BUILDKITE_COMMIT must be set}"
+container_name="xpu_${BUILDKITE_COMMIT}_$(
+    tr -dc A-Za-z0-9 </dev/urandom | head -c 10
+    echo
+)"
+
+cd "${omni_source_dir}"
+if [ -z "$(docker images -q "${base_image_name}")" ]; then
+    docker build --target vllm-base -t "${base_image_name}" --build-arg "VLLM_VERSION=${VLLM_VERSION}" -f docker/Dockerfile.xpu .
+fi
+
+# Try building the docker image
+docker build --build-arg "VLLM_BASE=${base_image_name}" --build-arg "VLLM_VERSION=${VLLM_VERSION}" -t "${image_name}" -f docker/Dockerfile.xpu .
+
+# Setup cleanup
+remove_docker_container() {
+    docker rm -f "${container_name}" || true
+    docker image rm -f "${image_name}" || true
+    docker system prune -f || true
+}
+trap remove_docker_container EXIT
+
+HF_CACHE="${HF_CACHE:-$(realpath ~)/.cache/huggingface}"
+mkdir -p "${HF_CACHE}"
+HF_MOUNT="/root/.cache/huggingface"
+
+time timeout -k 30 30m docker run \
+    --device /dev/dri:/dev/dri \
+    --net=host \
+    --ipc=host \
+    -v /dev/dri/by-path:/dev/dri/by-path \
+    -v "${HF_CACHE}:${HF_MOUNT}" \
+    --security-opt seccomp=unconfined \
+    --entrypoint="" \
+    -e VLLM_LOGGING_LEVEL \
+    -e VLLM_OMNI_LOGGING_LEVEL \
+    -e HF_TOKEN \
+    -e ZE_AFFINITY_MASK \
+    --name "${container_name}" \
+    "${image_name}" \
+    bash -c '
+    set -e
+    echo $ZE_AFFINITY_MASK
+    pip install tblib==3.1.0
+    cd /workspace/vllm-omni
+    pytest -v -s -m "core_model and xpu and B60"
+    export VLLM_XPU_USE_SAMPLER_KERNEL=0    # NOTE: Remove this after vLLM v0.21.1 is merged. Fixes Qwen2-5 omni-expansion tests.
+    pytest -v -s -m "advanced_model and xpu and B60"
+'

.buildkite/scripts/hardware_ci/run_npu_test.sh

@@ -0,0 +1,145 @@
+#!/bin/bash
+
+# This script build the Ascend NPU docker image and run the offline inference inside the container.
+# It serves a sanity check for compilation and basic model usage.
+set -ex
+
+# Base ubuntu image with basic ascend development libraries and python installed
+VLLM_OMNI_REPO="https://github.com/vllm-project/vllm-omni.git"
+BASE_IMAGE_NAME="quay.nju.edu.cn/ascend/vllm-ascend:v0.11.0rc2"
+image_name="npu/vllm-omni-ci:${BUILDKITE_COMMIT}_${EPOCHSECONDS}"
+# image_name="npu/vllm-ci:${BUILDKITE_COMMIT}_${EPOCHSECONDS}"
+container_name="npu_${BUILDKITE_COMMIT}_$(tr -dc A-Za-z0-9 < /dev/urandom | head -c 10; echo)"
+
+# BUILDKITE_AGENT_NAME format is {hostname}-{agent_idx}-{npu_card_num}cards
+agent_idx=$(echo "${BUILDKITE_AGENT_NAME}" | awk -F'-' '{print $(NF-1)}')
+echo "agent_idx: ${agent_idx}"
+builder_name="cachebuilder${agent_idx}"
+builder_cache_dir="/mnt/docker-cache${agent_idx}"
+mkdir -p ${builder_cache_dir}
+
+# Try building the docker image
+cat <<EOF | DOCKER_BUILDKIT=1 docker build \
+    --add-host pypi-cache:${PYPI_CACHE_HOST} \
+    --builder ${builder_name} --cache-from type=local,src=${builder_cache_dir} \
+                           --cache-to type=local,dest=${builder_cache_dir},mode=max \
+    --build-arg BUILDKITE_PULL_REQUEST="${BUILDKITE_PULL_REQUEST}" \
+    --build-arg BUILDKITE_PULL_REQUEST_REPO="${BUILDKITE_PULL_REQUEST_REPO}" \
+    --progress=plain --load -t ${image_name} -f - .
+FROM ${BASE_IMAGE_NAME}
+
+# Define environments
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN pip config set global.index-url http://pypi-cache:${PYPI_CACHE_PORT}/pypi/simple && \
+    pip config set global.trusted-host pypi-cache && \
+    apt-get update -y && \
+    apt-get install -y python3-pip git vim wget net-tools gcc g++ cmake libnuma-dev && \
+    rm -rf /var/cache/apt/* && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install for pytest to make the docker build cache layer always valid
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip install pytest>=6.0  pytest-cov modelscope
+
+COPY . .
+
+# Install vllm-omni
+WORKDIR /workspace
+ARG VLLM_OMNI_REPO=https://github.com/vllm-project/vllm-omni.git
+ARG VLLM_OMNI_TAG=main
+ARG BUILDKITE_PULL_REQUEST
+ARG BUILDKITE_PULL_REQUEST_REPO
+RUN git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf "https://github.com/" && \
+    if [ "\$BUILDKITE_PULL_REQUEST" != "false" ] && [ -n "\$BUILDKITE_PULL_REQUEST" ]; then \
+        echo "Cloning and checking out PR #\$BUILDKITE_PULL_REQUEST..." && \
+        git clone \$VLLM_OMNI_REPO /workspace/vllm-omni && \
+        cd /workspace/vllm-omni && \
+        git fetch origin pull/\$BUILDKITE_PULL_REQUEST/head:pr-\$BUILDKITE_PULL_REQUEST && \
+        git checkout pr-\$BUILDKITE_PULL_REQUEST; \
+    else \
+        echo "Not a PR build, using main branch" && \
+        git clone --depth 1 \$VLLM_OMNI_REPO /workspace/vllm-omni; \
+    fi
+
+RUN --mount=type=cache,target=/root/.cache/pip \
+    export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
+    source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
+    source /usr/local/Ascend/nnal/atb/set_env.sh && \
+    export LD_LIBRARY_PATH=\$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
+    python3 -m pip install -v -e /workspace/vllm-omni/
+
+ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
+
+WORKDIR /workspace/vllm-omni
+CMD ["/bin/bash"]
+
+EOF
+
+# Setup cleanup
+remove_docker_container() {
+  docker rm -f "${container_name}" || true;
+  docker image rm -f "${image_name}" || true;
+  docker system prune -f || true;
+}
+trap remove_docker_container EXIT
+
+# Generate corresponding --device args based on BUILDKITE_AGENT_NAME
+# Ascend NPU BUILDKITE_AGENT_NAME format is {hostname}-{agent_idx}-{npu_card_num}cards, and agent_idx starts from 1.
+#   e.g. atlas-a2-001-1-2cards means this is the 1-th agent on atlas-a2-001 host, and it has 2 NPU cards.
+#   returns --device /dev/davinci0 --device /dev/davinci1
+parse_and_gen_devices() {
+    local input="$1"
+    local index cards_num
+    if [[ "$input" =~ ([0-9]+)-([0-9]+)cards$ ]]; then
+        index="${BASH_REMATCH[1]}"
+        cards_num="${BASH_REMATCH[2]}"
+    else
+        echo "parse error" >&2
+        return 1
+    fi
+
+    local devices=""
+    local i=0
+    while (( i < cards_num )); do
+        local dev_idx=$(((index - 1)*cards_num + i ))
+        devices="$devices --device /dev/davinci${dev_idx}"
+        ((i++))
+    done
+
+    # trim leading space
+    devices="${devices#"${devices%%[![:space:]]*}"}"
+    # Output devices: assigned to the caller variable
+    printf '%s' "$devices"
+}
+
+devices=$(parse_and_gen_devices "${BUILDKITE_AGENT_NAME}") || exit 1
+
+# Run the image and execute the Out-Of-Tree (OOT) platform interface test case on Ascend NPU hardware.
+# This test checks whether the OOT platform interface is functioning properly in conjunction with
+# the hardware plugin vllm-ascend.
+hf_model_cache_dir=/mnt/hf_cache${agent_idx}
+ms_model_cache_dir=/mnt/modelscope${agent_idx}
+mkdir -p ${hf_model_cache_dir}
+mkdir -p ${ms_model_cache_dir}
+docker run \
+    --init \
+    ${devices} \
+    --device /dev/davinci_manager \
+    --device /dev/devmm_svm \
+    --device /dev/hisi_hdc \
+    -v /usr/local/dcmi:/usr/local/dcmi \
+    -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
+    -v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
+    -v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
+    -v /etc/ascend_install.info:/etc/ascend_install.info \
+    -v ${hf_model_cache_dir}:/root/.cache/huggingface \
+    -v ${ms_model_cache_dir}:/root/.cache/modelscope \
+    --network host \
+    --entrypoint="" \
+    --name "${container_name}" \
+    "${image_name}" \
+    bash -c '
+    set -e
+    VLLM_USE_MODELSCOPE=True pytest -s -v tests/e2e/offline_inference/test_qwen2_5_omni_expansion.py
+'

.buildkite/scripts/publish-release-images.sh

@@ -0,0 +1,50 @@
+#!/bin/bash
+# SPDX-License-Identifier: Apache-2.0
+#
+# Publish release Docker images from ECR to DockerHub.
+# Pulls per-arch images, tags with `latest` and versioned tags, pushes them,
+# then creates and pushes a multi-arch manifest.
+
+set -euo pipefail
+
+RELEASE_VERSION=$(buildkite-agent meta-data get release-version --default "" | sed 's/^v//')
+if [ -z "${RELEASE_VERSION}" ]; then
+  echo "ERROR: release-version metadata not set"
+  exit 1
+fi
+
+COMMIT="$BUILDKITE_COMMIT"
+DOCKERHUB_REPO="vllm/vllm-omni"
+ECR_REPO="public.ecr.aws/q9t5s3a7/vllm-omni-release-repo"
+
+echo "========================================"
+echo "Publishing release images v${RELEASE_VERSION}"
+echo "  Commit: ${COMMIT}"
+echo "========================================"
+
+# Login to ECR to pull staging images
+aws ecr-public get-login-password --region us-east-1 | \
+  docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7
+
+docker pull "${ECR_REPO}:${COMMIT}-x86_64"
+docker pull "${ECR_REPO}:${COMMIT}-aarch64"
+
+docker tag "${ECR_REPO}:${COMMIT}-x86_64" "${DOCKERHUB_REPO}:latest-x86_64"
+docker tag "${ECR_REPO}:${COMMIT}-x86_64" "${DOCKERHUB_REPO}:v${RELEASE_VERSION}-x86_64"
+docker push "${DOCKERHUB_REPO}:latest-x86_64"
+docker push "${DOCKERHUB_REPO}:v${RELEASE_VERSION}-x86_64"
+
+docker tag "${ECR_REPO}:${COMMIT}-aarch64" "${DOCKERHUB_REPO}:latest-aarch64"
+docker tag "${ECR_REPO}:${COMMIT}-aarch64" "${DOCKERHUB_REPO}:v${RELEASE_VERSION}-aarch64"
+docker push "${DOCKERHUB_REPO}:latest-aarch64"
+docker push "${DOCKERHUB_REPO}:v${RELEASE_VERSION}-aarch64"
+
+docker manifest rm "${DOCKERHUB_REPO}:latest" || true
+docker manifest rm "${DOCKERHUB_REPO}:v${RELEASE_VERSION}" || true
+docker manifest create "${DOCKERHUB_REPO}:latest" "${DOCKERHUB_REPO}:latest-x86_64" "${DOCKERHUB_REPO}:latest-aarch64"
+docker manifest create "${DOCKERHUB_REPO}:v${RELEASE_VERSION}" "${DOCKERHUB_REPO}:v${RELEASE_VERSION}-x86_64" "${DOCKERHUB_REPO}:v${RELEASE_VERSION}-aarch64"
+docker manifest push "${DOCKERHUB_REPO}:latest"
+docker manifest push "${DOCKERHUB_REPO}:v${RELEASE_VERSION}"
+
+echo ""
+echo "Successfully published release images for v${RELEASE_VERSION}"

.buildkite/scripts/upload_pipeline_with_skip_ci.sh

@@ -0,0 +1,146 @@
+#!/usr/bin/env bash
+# Evaluate docs-only skip-ci and upload continuation steps from the given pipeline YAML
+# (YAML document after the first `---`). Buildkite `if` is evaluated at upload time.
+#
+# Usage: upload_pipeline_with_skip_ci.sh [pipeline_yaml]
+#   pipeline_yaml: path relative to repo root or absolute (default: .buildkite/pipeline.yml)
+set -euo pipefail
+
+ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
+PIPELINE_ARG="${1:-.buildkite/pipeline.yml}"
+if [[ "${PIPELINE_ARG}" = /* ]]; then
+  PIPELINE_YML="${PIPELINE_ARG}"
+else
+  PIPELINE_YML="${ROOT}/${PIPELINE_ARG}"
+fi
+
+# Prints a single digit to stdout: 1 = skip image CI, 0 = run. Logs go to stderr.
+is_docs_only_change() {
+  local file_path
+  local has_any=0
+
+  while IFS= read -r file_path; do
+    [[ -z "${file_path}" ]] && continue
+    has_any=1
+
+    if [[ "${file_path}" == docs/* ]]; then
+      continue
+    fi
+    if [[ "${file_path}" == *.md ]]; then
+      continue
+    fi
+    if [[ "${file_path}" == "mkdocs.yml" ]]; then
+      continue
+    fi
+    return 1
+  done
+
+  [[ "${has_any}" -eq 1 ]]
+}
+
+resolve_skip_ci() {
+  local is_pr_build=0
+  local files
+  local base_branch base_ref
+
+  if [[ "${BUILDKITE_PULL_REQUEST:-false}" != "false" && -n "${BUILDKITE_PULL_REQUEST:-}" ]]; then
+    is_pr_build=1
+  fi
+
+  if [[ "${is_pr_build}" -eq 1 ]]; then
+    base_branch="${BUILDKITE_PULL_REQUEST_BASE_BRANCH:-main}"
+    if ! git rev-parse --verify "origin/${base_branch}" >/dev/null 2>&1; then
+      echo "resolve_skip_ci: origin/${base_branch} not found locally; trying fetch" >&2
+      git fetch --depth=200 origin "${base_branch}" >/dev/null 2>&1 || true
+    fi
+
+    base_ref=""
+    if git rev-parse --verify "origin/${base_branch}" >/dev/null 2>&1; then
+      base_ref="origin/${base_branch}"
+    elif git rev-parse --verify "${base_branch}" >/dev/null 2>&1; then
+      base_ref="${base_branch}"
+    else
+      echo "resolve_skip_ci: cannot resolve PR base ${base_branch}; skip-ci=0" >&2
+      echo -n 0
+      return 0
+    fi
+
+    if ! files="$(git diff --name-only "${base_ref}...${BUILDKITE_COMMIT}" 2>/dev/null)"; then
+      echo "resolve_skip_ci: failed to compute PR changed files; skip-ci=0" >&2
+      echo -n 0
+      return 0
+    fi
+  elif [[ "${BUILDKITE_BRANCH:-}" == "main" ]]; then
+    if ! git rev-parse --verify "${BUILDKITE_COMMIT}^" >/dev/null 2>&1; then
+      echo "resolve_skip_ci: commit has no parent on main; skip-ci=0" >&2
+      echo -n 0
+      return 0
+    fi
+    if ! files="$(git diff --name-only "${BUILDKITE_COMMIT}^..${BUILDKITE_COMMIT}" 2>/dev/null)"; then
+      echo "resolve_skip_ci: failed to compute main changed files; skip-ci=0" >&2
+      echo -n 0
+      return 0
+    fi
+  else
+    echo "resolve_skip_ci: not PR/main build; skip-ci=0" >&2
+    echo -n 0
+    return 0
+  fi
+
+  if is_docs_only_change <<< "${files}"; then
+    echo "resolve_skip_ci: docs-only change detected; skip-ci=1" >&2
+    echo -n 1
+    return 0
+  fi
+
+  echo "resolve_skip_ci: non-doc changes detected; skip-ci=0" >&2
+  echo -n 0
+}
+
+SKIP_CI="$(resolve_skip_ci)"
+
+if [[ ! -f "${PIPELINE_YML}" ]]; then
+  echo "upload_pipeline_with_skip_ci: missing ${PIPELINE_YML}" >&2
+  exit 1
+fi
+
+export ROOT SKIP_CI PIPELINE_YML
+python3 <<'PY' | buildkite-agent pipeline upload
+import os
+import pathlib
+
+path = pathlib.Path(os.environ["PIPELINE_YML"])
+text = path.read_text(encoding="utf-8")
+sep = "\n---\n"
+# Two supported layouts:
+#   - multi-doc: doc 1 = bootstrap (loaded by Buildkite), doc 2 (after `---`) = uploaded steps.
+#   - single-doc: whole file is the uploaded steps; caller (UI init step) is the bootstrap.
+if sep in text:
+    _, continuation = text.split(sep, 1)
+else:
+    continuation = text
+
+skip = os.environ.get("SKIP_CI") == "1"
+# When docs-only skip-ci: skip default CI image, but still build for L4 nightly (PR label nightly-test or
+# main NIGHTLY=1), otherwise upload-nightly (depends_on image-build) would be skipped too.
+nightly_only = (
+    '(build.pull_request.labels includes "nightly-test") '
+    '|| (build.branch == "main" && build.env("NIGHTLY") == "1")'
+)
+# Placeholder in pipeline.yml is `if: __IMAGE_BUILD_IF__` (valid YAML); replace value only.
+if skip:
+    rep = f"'{nightly_only}'"
+    ready_rep = "'false'"
+    merge_rep = "'false'"
+else:
+    rep = "'true'"
+    ready_rep = "'build.branch != \"main\" && build.pull_request.labels includes \"ready\"'"
+    merge_rep = "'(build.branch == \"main\" && build.env(\"NIGHTLY\") != \"1\" && build.env(\"WEEKLY\") != \"1\") || (build.branch != \"main\" && build.pull_request.labels includes \"merge-test\")'"
+rendered = (
+    continuation
+    .replace("__IMAGE_BUILD_IF__", rep)
+    .replace("__UPLOAD_READY_IF__", ready_rep)
+    .replace("__UPLOAD_MERGE_IF__", merge_rep)
+)
+print(rendered, end="")
+PY

.buildkite/test-amd-merge.yml

@@ -0,0 +1,219 @@
+steps:
+
+- label: "Simple Unit Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_ROCM_USE_AITER=0
+    # ignore test_teacache_extractors.py because it use rocm gemm kernel from vLLM
+    # that is not supported on CPU
+    - "timeout 60m pytest -v -s -m 'core_model and cpu' --ignore=tests/diffusion/cache/test_teacache_extractors.py --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
+
+- label: "Diffusion Images API LoRA E2E"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - timeout 20m pytest -s -v tests/diffusion/lora/test_images_generations_lora.py
+
+- label: "Diffusion Model CPU offloading Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - |
+      timeout 20m bash -c '
+        set +e
+        pytest -s -v tests/diffusion/offloader/test_diffusion_cpu_offload.py
+        EXIT1=\$?
+        pytest -s -v tests/diffusion/offloader/test_diffusion_layerwise_offload.py
+        EXIT2=\$?
+        exit \$((EXIT1 | EXIT2))
+      '
+
+## ISSUE depends on `diffusers` package: https://github.com/huggingface/diffusers/issues/13274
+# - label: "Audio Generation Model Test"
+#   agent_pool: mi325_1
+#   depends_on: amd-build
+#   mirror_hardwares: [amdproduction]
+#   grade: Blocking
+#   commands:
+#     - export GPU_ARCHS=gfx942
+#     - export VLLM_LOGGING_LEVEL=DEBUG
+#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+#     - timeout 20m pytest -s -v tests/e2e/offline_inference/test_stable_audio_expansion.py -m "advanced_model and diffusion and L4" --run-level advanced_model
+
+- label: "Diffusion Cache Backend Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - timeout 15m pytest -s -v -m "core_model and cache and diffusion and not distributed_cuda and L4"
+
+- label: "Diffusion Sequence Parallelism Test (Need 4 GPUs)"
+  agent_pool: mi325_4
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - timeout 20m pytest -s -v tests/diffusion/distributed/test_sequence_parallel.py
+    - timeout 20m pytest -s -v tests/diffusion/distributed/test_ulysses_uaa_perf.py
+
+# merge-only tests
+- label: "Diffusion Tensor Parallelism Test"
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - pytest -s -v tests/diffusion/distributed/test_zimage_parallelism.py
+
+- label: "Diffusion Model Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - timeout 30m pytest -s -v tests/e2e/offline_inference/test_z_image.py
+
+- label: "Diffusion GPU Worker Test"
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - timeout 20m pytest -s -v tests/diffusion/test_diffusion_worker.py
+
+- label: "Engine Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - timeout 20m pytest -s -v tests/engine/test_async_omni_engine_abort.py
+
+# This is from test-nightly.yml.
+# This model seems to be important, so I am trying to run it here.
+# Since this is from test-nightly.yml,
+# I keep this non-blocking.
+- label: "Omni Model Test Qwen2-5-Omni"
+  agent_pool: mi325_4
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  commands:
+    - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
+    - pytest -s -v tests/e2e/*/test_qwen2_5_omni_expansion.py --run-level "core_model"
+
+- label: "Omni Model Test Qwen3-Omni"
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py tests/e2e/online_serving/test_mimo_audio.py -m "advanced_model" --run-level "advanced_model"
+
+- label: "Qwen3-TTS CustomVoice E2E Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - |
+      timeout 20m bash -c '
+        export VLLM_LOGGING_LEVEL=DEBUG
+        export VLLM_WORKER_MULTIPROC_METHOD=spawn
+        export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
+        pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py tests/e2e/offline_inference/test_qwen3_tts_customvoice.py -m "advanced_model" --run-level "advanced_model"
+      '
+
+- label: "Qwen3-TTS Base E2E Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - |
+      timeout 30m bash -c '
+        export VLLM_LOGGING_LEVEL=DEBUG
+        export VLLM_WORKER_MULTIPROC_METHOD=spawn
+        export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
+        pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py tests/e2e/offline_inference/test_qwen3_tts_base.py -m "advanced_model" --run-level "advanced_model"
+      '
+
+# TODO: Bagel test on ROCm is very unstable. @tjtanaa
+# Need to debug before reneable numerical changes across large PRs
+# # split Bagel Model Test with H100 (Real Weights) into three tests
+# - label: "Bagel Text2Img Model Test (1/3)"
+#   agent_pool: mi325_1
+#   depends_on: amd-build
+#   mirror_hardwares: [amdproduction]
+#   grade: Blocking
+#   commands:
+#     - export GPU_ARCHS=gfx942
+#     - export VLLM_LOGGING_LEVEL=DEBUG
+#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
+#     - timeout 30m pytest -s -v tests/e2e/offline_inference/test_bagel.py -m "advanced_model" --run-level "advanced_model" -k "shared_memory" -k "rocm"
+
+# - label: "Bagel Img2Img Model Test (2/3)"
+#   agent_pool: mi325_1
+#   depends_on: amd-build
+#   mirror_hardwares: [amdproduction]
+#   grade: Blocking
+#   commands:
+#     - export GPU_ARCHS=gfx942
+#     - export VLLM_LOGGING_LEVEL=DEBUG
+#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
+#     - timeout 30m pytest -s -v tests/e2e/offline_inference/test_bagel.py -m "advanced_model" --run-level "advanced_model" -k "rocm"
+
+# - label: "Bagel Online Serving Test (3/3)"
+#   agent_pool: mi325_1
+#   depends_on: amd-build
+#   mirror_hardwares: [amdproduction]
+#   grade: Blocking
+#   commands:
+#     - export GPU_ARCHS=gfx942
+#     - export VLLM_IMAGE_FETCH_TIMEOUT=60
+#     - export VLLM_LOGGING_LEVEL=DEBUG
+#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
+#     - timeout 40m pytest -s -v tests/e2e/online_serving/test_bagel.py -m "advanced_model" --run-level "advanced_model" -k "rocm"
+
+- label: "Diffusion · Wan22 Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - |
+      timeout 40m bash -c "
+        export VLLM_IMAGE_FETCH_TIMEOUT=60
+        pytest -s -v tests/e2e/offline_inference/test_wan22_t2v.py tests/e2e/online_serving/test_wan22_t2v.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model'
+      "
+
+- label: "Voxtral-TTS E2E Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - |
+      timeout 20m bash -c '
+        export VLLM_LOGGING_LEVEL=DEBUG
+        export VLLM_WORKER_MULTIPROC_METHOD=spawn
+        pytest -s -v tests/e2e/online_serving/test_voxtral_tts.py tests/e2e/offline_inference/test_voxtral_tts.py -m "advanced_model" --run-level "advanced_model"
+      '

.buildkite/test-amd-ready.yaml

@@ -0,0 +1,227 @@
+steps:
+
+- label: "Simple Unit Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_ROCM_USE_AITER=0
+    # ignore test_teacache_extractors.py because it use rocm gemm kernel from vLLM
+    # that is not supported on CPU
+    - "timeout 60m pytest -v -s -m 'core_model and cpu' --ignore=tests/diffusion/cache/test_teacache_extractors.py --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
+
+- label: "Voxtral TTS CUDA Unit Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - timeout 10m pytest -s -v tests/model_executor/models/voxtral_tts/test_cuda_graph_acoustic_transformer.py
+
+- label: "Diffusion Batching Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - timeout 20m pytest -s -v tests/diffusion/batching/test_diffusion_batching.py -m "core_model and diffusion" --run-level "core_model"
+
+- label: "Custom Pipeline Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - timeout 20m pytest -s -v tests/e2e/offline_inference/custom_pipeline/ -m "core_model"
+
+- label: "Diffusion Model CPU offloading Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - |
+      timeout 20m bash -c '
+        set +e
+        pytest -s -v tests/diffusion/offloader/test_diffusion_cpu_offload.py
+        EXIT1=\$?
+        pytest -s -v tests/diffusion/offloader/test_diffusion_layerwise_offload.py
+        EXIT2=\$?
+        exit \$((EXIT1 | EXIT2))
+      '
+
+## ISSUE depends on `diffusers` package: https://github.com/huggingface/diffusers/issues/13274
+# - label: "Audio Generation Model Test"
+#   agent_pool: mi325_1
+#   depends_on: amd-build
+#   mirror_hardwares: [amdproduction]
+#   grade: Blocking
+#   commands:
+#     - export GPU_ARCHS=gfx942
+#     - export VLLM_LOGGING_LEVEL=DEBUG
+#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+#     - timeout 20m pytest -s -v tests/e2e/offline_inference/test_stable_audio_expansion.py -m "advanced_model and diffusion and L4" --run-level advanced_model
+
+- label: "Diffusion Cache Backend Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export GPU_ARCHS=gfx942
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - timeout 15m pytest -s -v -m "core_model and cache and diffusion and not distributed_cuda and L4"
+
+- label: "Diffusion Sequence Parallelism Test"
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - timeout 20m pytest -s -v tests/diffusion/distributed/test_sequence_parallel.py -m core_model
+
+- label: "Diffusion GPU Worker Test"
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - timeout 20m pytest -s -v tests/diffusion/test_diffusion_worker.py
+
+- label: "Diffusion · Model Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - timeout 15m pytest -sv tests/diffusion/models/ -m 'core_model and cuda' --run-level "core_model"
+
+- label: "Diffusion · Wan22 Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - |
+      timeout 40m bash -c "
+        export VLLM_TEST_CLEAN_GPU_MEMORY=1
+        export VLLM_IMAGE_FETCH_TIMEOUT=60
+        pytest -s -v tests/e2e/online_serving/test_wan22_t2v.py -m 'core_model' --run-level 'core_model'
+      "
+
+- label: "Engine Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - |
+      timeout 15m bash -c '
+              pytest -s -v tests/engine/test_async_omni_engine_abort.py
+      '
+
+# - label: "Omni Model Test Qwen3-Omni"
+#   agent_pool: mi325_2
+#   depends_on: amd-build
+#   mirror_hardwares: [amdproduction]
+#   grade: Blocking
+#   commands:
+#     - export VLLM_LOGGING_LEVEL=DEBUG
+#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+#     - timeout 10m pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
+#     - timeout 20m pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m "core_model" --run-level "core_model"
+
+- label: "MiMo-Audio E2E Test with H100"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - |
+      timeout 30m bash -c '
+        export VLLM_LOGGING_LEVEL=DEBUG
+        export VLLM_WORKER_MULTIPROC_METHOD=spawn
+        pytest -s -v tests/e2e/online_serving/test_mimo_audio.py -m "core_model" --run-level "core_model"
+      '
+
+- label: "Qwen3-TTS E2E Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
+    - timeout 30m pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m "core_model" --run-level "core_model"
+
+- label: "Voxtral-TTS E2E Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - |
+      timeout 20m bash -c '
+        export VLLM_LOGGING_LEVEL=DEBUG
+        export VLLM_WORKER_MULTIPROC_METHOD=spawn
+        pytest -s -v tests/e2e/online_serving/test_voxtral_tts.py -m "advanced_model" --run-level "advanced_model"
+        pytest -s -v tests/e2e/offline_inference/test_voxtral_tts.py -m "advanced_model" --run-level "advanced_model"
+      '
+
+# TODO: Bagel test on ROCm is very unstable. @tjtanaa
+# Need to debug before reneable numerical changes across large PRs
+# - label: "Bagel Text2Img Model Test"
+#   agent_pool: mi325_1
+#   depends_on: amd-build
+#   mirror_hardwares: [amdproduction]
+#   grade: Blocking
+#   commands:
+#     - export GPU_ARCHS=gfx942
+#     - export VLLM_LOGGING_LEVEL=DEBUG
+#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
+#     - timeout 30m pytest -s -v tests/e2e/offline_inference/test_bagel.py -m "core_model" --run-level "core_model" -k "rocm"
+
+# - label: "Bagel Img2Img Model Test"
+#   agent_pool: mi325_1
+#   depends_on: amd-build
+#   mirror_hardwares: [amdproduction]
+#   grade: Blocking
+#   commands:
+#     - export GPU_ARCHS=gfx942
+#     - export VLLM_LOGGING_LEVEL=DEBUG
+#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
+#     - timeout 30m pytest -s -v tests/e2e/offline_inference/test_bagel.py -m "core_model" --run-level "core_model" -k "rocm"
+
+# - label: "Bagel Online Serving Test"
+#   agent_pool: mi325_1
+#   depends_on: amd-build
+#   mirror_hardwares: [amdproduction]
+#   grade: Blocking
+#   commands:
+#     - export GPU_ARCHS=gfx942
+#     - export VLLM_IMAGE_FETCH_TIMEOUT=60
+#     - export VLLM_LOGGING_LEVEL=DEBUG
+#     - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+#     - export VLLM_ROCM_USE_AITER_RMSNORM=0
+#     - timeout 40m pytest -s -v tests/e2e/online_serving/test_bagel.py -m "core_model" --run-level "core_model" -k "rocm"
+
+- label: "CosyVoice3-TTS E2E Test"
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - |
+      timeout 20m bash -c '
+        pytest -s -v tests/e2e/online_serving/test_cosyvoice3_tts_expansion.py -m "full_model" --run-level "core_model"
+      '

.buildkite/test-amd.yaml

@@ -0,0 +1,118 @@
+steps:
+
+- label: "Diffusion Model Test"
+  timeout_in_minutes: 30
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export GPU_ARCHS=gfx942
+    - pytest -s -v tests/e2e/offline_inference/test_z_image.py
+
+- label: "Diffusion Images API LoRA E2E"
+  timeout_in_minutes: 30
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export GPU_ARCHS=gfx942
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pytest -s -v tests/diffusion/lora/test_images_generations_lora.py
+
+- label: "Diffusion Model CPU offloading Test"
+  timeout_in_minutes: 20
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export GPU_ARCHS=gfx942
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pytest -s -v tests/diffusion/offloader/test_diffusion_cpu_offload.py
+    - pytest -s -v tests/diffusion/offloader/test_diffusion_layerwise_offload.py
+
+- label: "Diffusion Cache Backend Test"
+  timeout_in_minutes: 15
+  agent_pool: mi325_1
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export GPU_ARCHS=gfx942
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pytest -s -v -m 'core_model and cache and diffusion and not distributed_rocm and MI325'
+
+- label: "Diffusion Sequence Parallelism Test"
+  timeout_in_minutes: 20
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export GPU_ARCHS=gfx942
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pytest -s -v tests/diffusion/distributed/test_sequence_parallel.py -m core_model
+
+- label: "Diffusion Tensor Parallelism Test"
+  timeout_in_minutes: 20
+  agent_pool: mi325_2
+  depends_on: amd-build
+  commands:
+    - export GPU_ARCHS=gfx942
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pytest -s -v tests/diffusion/distributed/test_zimage_parallelism.py
+
+- label: "Diffusion GPU Worker Test"
+  timeout_in_minutes: 20
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - pytest -s -v tests/diffusion/test_diffusion_worker.py
+
+- label: "Omni Model Test Qwen2-5-Omni"
+  timeout_in_minutes: 15
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export GPU_ARCHS=gfx942
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pytest -s -v tests/e2e/offline_inference/test_qwen2_5_omni_expansion.py
+    - pytest -s -v tests/engine/test_async_omni_engine_abort.py
+
+- label: "Omni Model Test Qwen3-Omni"
+  timeout_in_minutes: 15
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - export VLLM_ROCM_USE_AITER=0
+    - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
+    - pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py
+
+
+- label: "Omni Sleep Mode Test"
+  timeout_in_minutes: 40
+  agent_pool: mi325_2
+  depends_on: amd-build
+  mirror_hardwares: [amdproduction]
+  grade: Blocking
+  commands:
+    - export GPU_ARCHS=gfx942
+    - export VLLM_LOGGING_LEVEL=DEBUG
+    - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+    - pytest -s -v tests/entrypoints/test_omni_sleep_mode.py -m "advanced_model and omni and MI325" --run-level "advanced_model"

.buildkite/test-merge.yml

@@ -0,0 +1,742 @@
+env:
+  VLLM_WORKER_MULTIPROC_METHOD: spawn
+  VLLM_USE_FLASHINFER_MOE_FP16: 0
+  HF_HUB_DOWNLOAD_TIMEOUT: 300
+  HF_HUB_ETAG_TIMEOUT: 60
+
+steps:
+  - group: ":card_index_dividers: Simple Test"
+    depends_on: upload-merge-pipeline
+    steps:
+      - label: "Simple · Diffusion & Model Executor Test"
+        commands:
+          - "timeout 20m pytest -sv tests/diffusion tests/model_executor -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
+        agents:
+          queue: "gpu_1_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Simple · Other Test"
+        commands:
+          - "timeout 20m pytest -sv -m 'core_model and cpu' --ignore=tests/diffusion --ignore=tests/model_executor --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
+        agents:
+          queue: "gpu_1_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+  - group: ":card_index_dividers: Diffusion Test"
+    depends_on: upload-merge-pipeline
+    steps:
+      - label: "Diffusion · LoRA Test"
+        timeout_in_minutes: 30
+        commands:
+          - pytest -sv tests/diffusion/lora/ -m 'advanced_model and cuda' --run-level "advanced_model"
+        agents:
+          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+  - label: "Distributed Test"
+    timeout_in_minutes: 60
+    commands:
+      - |
+        timeout 55m bash -c "
+          set -e
+          export VLLM_IMAGE_FETCH_TIMEOUT=60
+          pytest -s -v tests/distributed -m 'advanced_model and cuda' --run-level 'advanced_model'
+        "
+    agents:
+      queue: "mithril-h100-pool"
+    plugins:
+      - kubernetes:
+          podSpec:
+            containers:
+              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                resources:
+                  limits:
+                    nvidia.com/gpu: 1
+                volumeMounts:
+                  - name: devshm
+                    mountPath: /dev/shm
+                  - name: hf-cache
+                    mountPath: /root/.cache/huggingface
+                env:
+                  - name: HF_HOME
+                    value: /root/.cache/huggingface
+                  - name: HF_TOKEN
+                    valueFrom:
+                      secretKeyRef:
+                        name: hf-token-secret
+                        key: token
+            nodeSelector:
+              node.kubernetes.io/instance-type: gpu-h100-sxm
+            volumes:
+              - name: devshm
+                emptyDir:
+                  medium: Memory
+              - name: hf-cache
+                hostPath:
+                  path: /mnt/hf-cache
+                  type: DirectoryOrCreate
+
+  - group: ":card_index_dividers: Entrypoints Test"
+    depends_on: upload-merge-pipeline
+    steps:
+      - label: "Entrypoint Test with H100"
+        timeout_in_minutes: 35
+        commands:
+          - pytest -s -v tests/entrypoints/ -m "advanced_model and cuda and H100" --run-level "advanced_model"
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 2
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Entrypoint Test with L4"
+        timeout_in_minutes: 30
+        commands:
+          - pytest -s -v tests/entrypoints/ -m "advanced_model and cuda and L4" --run-level "advanced_model"
+        agents:
+          queue: "gpu_4_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+  - group: ":card_index_dividers: E2E Test"
+    depends_on: upload-merge-pipeline
+    steps:
+      - label: "TTS · Qwen3-TTS CustomVoice Test"
+        commands:
+          - |
+            timeout 20m bash -c "
+              export VLLM_LOGGING_LEVEL=DEBUG
+              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
+              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py tests/e2e/offline_inference/test_qwen3_tts_customvoice.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+            "
+        agents:
+          queue: "gpu_4_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              shm-size: "8gb"
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "TTS · Qwen3-TTS Base Test"
+        commands:
+          - |
+            timeout 20m bash -c "
+              export VLLM_LOGGING_LEVEL=DEBUG
+              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
+              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py tests/e2e/offline_inference/test_qwen3_tts_base.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+            "
+        agents:
+          queue: "gpu_4_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              shm-size: "8gb"
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "TTS · Voxtral-TTS Test"
+        timeout_in_minutes: 20
+        commands:
+          - |
+            timeout 20m bash -c "
+              export VLLM_LOGGING_LEVEL=DEBUG
+              pytest -s -v tests/e2e/offline_inference/test_voxtral_tts.py tests/e2e/online_serving/test_voxtral_tts.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+
+      - label: "Omni · Qwen3-Omni Test"
+        timeout_in_minutes: 30
+        commands:
+          - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 2
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Omni · Mimo Audio Test"
+        timeout_in_minutes: 30
+        commands:
+          - pytest -s -v tests/e2e/online_serving/test_mimo_audio.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 2
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Omni · VoxCPM2 Test"
+        timeout_in_minutes: 20
+        commands:
+          - |
+            timeout 20m bash -c "
+              export VLLM_LOGGING_LEVEL=DEBUG
+              export VLLM_WORKER_MULTIPROC_METHOD=spawn
+              pytest -s -v tests/e2e/offline_inference/test_voxcpm2.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+            "
+        agents:
+          queue: "gpu_1_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              shm-size: "8gb"
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Diffusion · Qwen Image Edit Test"
+        timeout_in_minutes: 20
+        commands:
+          - pytest -s -v tests/e2e/online_serving/test_qwen_image_edit.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Diffusion · Longcat Image Edit Test"
+        timeout_in_minutes: 20
+        commands:
+          - pytest -s -v tests/e2e/online_serving/test_longcat_image_edit.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Diffusion · Longcat Image Test"
+        timeout_in_minutes: 20
+        commands:
+          - pytest -s -v tests/e2e/online_serving/test_longcat_image.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Diffusion · Bagel Test"
+        timeout_in_minutes: 20
+        commands:
+          - pytest -s -v tests/e2e/offline_inference/test_bagel.py tests/e2e/online_serving/test_bagel.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+
+      - label: "Diffusion · Qwen Image Test"
+        commands:
+          - |
+            timeout 40m bash -c '
+              export VLLM_IMAGE_FETCH_TIMEOUT=60
+              pytest -s -v tests/e2e/online_serving/test_qwen_image.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+            '
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Diffusion · Qwen Image Layered Test"
+        commands:
+          - |
+            timeout 40m bash -c "
+              export VLLM_IMAGE_FETCH_TIMEOUT=60
+              pytest -s -v tests/e2e/online_serving/test_qwen_image_layered.py -m 'advanced_model and cuda' --run-level 'advanced_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Diffusion · Wan22 Test"
+        commands:
+          - |
+            timeout 40m bash -c "
+              export VLLM_IMAGE_FETCH_TIMEOUT=60
+              pytest -s -v tests/e2e/offline_inference/test_wan22_t2v.py tests/e2e/online_serving/test_wan22_t2v.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Diffusion · HunyuanVideo 1.5 Test"
+        timeout_in_minutes: 40
+        commands:
+          - |
+            timeout 40m bash -c "
+              pytest -s -v tests/e2e/online_serving/test_hunyuan_video_15.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Diffusion · Z Image Test"
+        timeout_in_minutes: 30
+        commands:
+          - pytest -s -v tests/e2e/offline_inference/test_z_image.py tests/e2e/online_serving/test_z_image.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model'
+        agents:
+          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Diffusion · FLUX.2 Klein Test"
+        timeout_in_minutes: 30
+        commands:
+          - pytest -s -v tests/e2e/offline_inference/test_flux2_klein.py tests/e2e/online_serving/test_flux2_klein.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model'
+        agents:
+          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Diffusion · SD3 Test"
+        timeout_in_minutes: 45
+        commands:
+          - |
+            timeout 45m bash -c "
+              export VLLM_IMAGE_FETCH_TIMEOUT=60
+              pytest -s -v tests/e2e/online_serving/test_sd3.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 4
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate

.buildkite/test-npu-nightly.yaml

@@ -0,0 +1,24 @@
+steps:
+  - group: ":card_index_dividers: Diffusion X2V Model Test"
+    key: nightly-diffusion-x2v-group
+    depends_on: upload-nightly-pipeline
+    if: >-
+      build.env("NIGHTLY") == "1" ||
+      build.pull_request.labels includes "nightly-test" ||
+      build.pull_request.labels includes "diffusion-x2v-test"
+    steps:
+      - label: ":full_moon: Diffusion X2V · Function Test"
+        agents:
+          queue: "ascend-a2b3"
+          resource_class: "npu-4"
+        image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}"
+        plugins:
+          - kubernetes:
+              podSpecPatch:
+                imagePullSecrets:
+                  - name: swr-secret
+        env:
+          VLLM_WORKER_MULTIPROC_METHOD: spawn
+          HF_TOKEN: "${HF_TOKEN}"
+        commands:
+          - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k npu_i2v --run-level "full_model"

.buildkite/test-npu-ready.yaml

@@ -0,0 +1,21 @@
+steps:
+  - group: ":card_index_dividers: TTS Model Test"
+    key: ready-tts-group
+    depends_on: upload-ready-pipeline
+    steps:
+      - label: ":sound: TTS · Qwen3-TTS CustomVoice Test"
+        agents:
+          queue: "ascend-a2b3"
+          resource_class: "npu-1"
+        image: "swr.cn-southwest-2.myhuaweicloud.com/modelfoundry/vllm-omni-ci-npu:${BUILDKITE_COMMIT}"
+        plugins:
+          - kubernetes:
+              podSpecPatch:
+                imagePullSecrets:
+                  - name: swr-secret
+        env:
+          VLLM_WORKER_MULTIPROC_METHOD: spawn
+          VLLM_ALLOW_LONG_MAX_MODEL_LEN: "1"
+          HF_TOKEN: "${HF_TOKEN}"
+        commands:
+          - pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m 'core_model' --run-level 'core_model'

.buildkite/test-ready.yml

@@ -0,0 +1,541 @@
+env:
+  VLLM_WORKER_MULTIPROC_METHOD: spawn
+  VLLM_USE_FLASHINFER_MOE_FP16: 0
+  HF_HUB_DOWNLOAD_TIMEOUT: 300
+  HF_HUB_ETAG_TIMEOUT: 60
+
+steps:
+  - group: ":card_index_dividers: Simple Test"
+    depends_on: upload-ready-pipeline
+    steps:
+      - label: "Simple · Diffusion & Model Executor Test"
+        commands:
+          - "timeout 20m pytest -sv tests/diffusion tests/model_executor -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
+        agents:
+          queue: "gpu_1_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Simple · Other Test"
+        commands:
+          - "timeout 20m pytest -sv -m 'core_model and cpu' --ignore=tests/diffusion --ignore=tests/model_executor --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
+        agents:
+          queue: "gpu_1_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+  - label: "Custom Pipeline Test"
+    depends_on: upload-ready-pipeline
+    commands:
+      - timeout 20m pytest -s -v tests/e2e/offline_inference/custom_pipeline/ -m "core_model"
+    agents:
+      queue: "gpu_1_queue"
+    plugins:
+      - docker#v5.2.0:
+          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+          always-pull: true
+          propagate-environment: true
+          environment:
+            - "HF_HOME=/fsx/hf_cache"
+          volumes:
+            - "/fsx/hf_cache:/fsx/hf_cache"
+
+  - group: ":card_index_dividers: Diffusion Test"
+    depends_on: upload-ready-pipeline
+    steps:
+      - label: "Diffusion · Offloader Test"
+        commands:
+          - timeout 10m pytest -s -v tests/diffusion/offloader -m "core_model and cuda" --run-level "core_model"
+        agents:
+          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Diffusion · Cache Test"
+        commands:
+          - timeout 15m pytest -sv tests/diffusion/cache -m 'core_model and cuda' --run-level "core_model"
+        agents:
+          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Diffusion · Batch Test"
+        commands:
+          - timeout 15m pytest -sv tests/diffusion/batching -m 'core_model and cuda' --run-level "core_model"
+        agents:
+          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Diffusion · Distributed Test"
+        commands:
+          - timeout 20m pytest -sv tests/diffusion/distributed -m 'core_model and cuda' --run-level "core_model"
+        agents:
+          queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              shm-size: "8gb"
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Diffusion · Model Test"
+        commands:
+          - timeout 15m pytest -sv tests/diffusion/models/ -m 'core_model and cuda' --run-level "core_model"
+        agents:
+          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Diffusion · Other Test"
+        commands:
+          - timeout 15m pytest -sv tests/diffusion/*.py -m 'core_model and cuda' --run-level "core_model"
+        agents:
+          queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+
+  - label: "Engine&Model Executor Test"
+    depends_on: upload-ready-pipeline
+    commands:
+      - |
+        timeout 15m bash -c "
+                  pytest -sv tests/engine/ tests/model_executor/ -m 'core_model and cuda' --run-level 'core_model'
+        "
+    agents:
+      queue: "gpu_1_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
+    plugins:
+      - docker#v5.2.0:
+          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+          always-pull: true
+          propagate-environment: true
+          shm-size: "8gb"
+          environment:
+            - "HF_HOME=/fsx/hf_cache"
+            - "HF_TOKEN"
+          volumes:
+            - "/fsx/hf_cache:/fsx/hf_cache"
+
+
+  - label: "Distributed Test"
+    depends_on: upload-ready-pipeline
+    commands:
+      - |
+        timeout 15m bash -c "
+                  pytest -sv tests/distributed/ -m 'core_model and cuda' --run-level 'core_model'
+        "
+    agents:
+      queue: "mithril-h100-pool"
+    plugins:
+      - kubernetes:
+          podSpec:
+            containers:
+              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                resources:
+                  limits:
+                    nvidia.com/gpu: 1
+                volumeMounts:
+                  - name: devshm
+                    mountPath: /dev/shm
+                  - name: hf-cache
+                    mountPath: /root/.cache/huggingface
+                env:
+                  - name: HF_HOME
+                    value: /root/.cache/huggingface
+            nodeSelector:
+              node.kubernetes.io/instance-type: gpu-h100-sxm
+            volumes:
+              - name: devshm
+                emptyDir:
+                  medium: Memory
+              - name: hf-cache
+                hostPath:
+                  path: /mnt/hf-cache
+                  type: DirectoryOrCreate
+
+  - group: ":card_index_dividers: E2E Test"
+    depends_on: upload-ready-pipeline
+    steps:
+      - label: "RLHF · VeRL-Omni E2E Test"
+        commands:
+          - |
+            timeout 20m bash -c "
+              pytest -s -v tests/e2e/offline_inference/rlhf_test/test_verl_omni_e2e.py
+            "
+        agents:
+          queue: "gpu_1_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              shm-size: "8gb"
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Omni · Qwen3-Omni Test"
+        commands:
+          - |
+            timeout 20m bash -c "
+              pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m 'core_model' --run-level 'core_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 2
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Omni · VoxCPM2 Test"
+        timeout_in_minutes: 20
+        commands:
+          - |
+            timeout 20m bash -c "
+              export VLLM_LOGGING_LEVEL=DEBUG
+              export VLLM_WORKER_MULTIPROC_METHOD=spawn
+              pytest -s -v tests/e2e/offline_inference/test_voxcpm2.py -m 'core_model' --run-level 'core_model'
+            "
+        agents:
+          queue: "gpu_1_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              shm-size: "8gb"
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "TTS · Qwen3-TTS CustomVoice Test"
+        commands:
+          - |
+            timeout 20m bash -c "
+              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
+              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m 'core_model' --run-level 'core_model'
+            "
+        agents:
+          queue: "gpu_4_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              shm-size: "8gb"
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "TTS · Qwen3-TTS Base Test"
+        commands:
+          - |
+            timeout 20m bash -c "
+              export VLLM_WORKER_MULTIPROC_METHOD=spawn
+              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
+              export VLLM_OMNI_USE_V2_RUNNER=1
+              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py -m 'core_model' --run-level 'core_model'
+            "
+        agents:
+          queue: "gpu_4_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              shm-size: "8gb"
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"
+
+      - label: "Diffusion · Qwen Image Edit Test"
+        commands:
+          - |
+            timeout 20m bash -c "
+              pytest -s -v tests/e2e/online_serving/test_qwen_image_edit.py -m 'core_model' --run-level 'core_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Diffusion · Bagel Test"
+        commands:
+          - |
+            timeout 40m bash -c "
+              export VLLM_IMAGE_FETCH_TIMEOUT=60
+              pytest -s -v tests/e2e/online_serving/test_bagel.py -m 'core_model' --run-level 'core_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Diffusion · Wan22 Test"
+        commands:
+          - |
+            timeout 40m bash -c "
+              export VLLM_IMAGE_FETCH_TIMEOUT=60
+              pytest -s -v tests/e2e/online_serving/test_wan22_t2v.py -m 'core_model' --run-level 'core_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+
+      - label: "Diffusion · Qwen Image Test"
+        commands:
+          - |
+            timeout 40m bash -c "
+              export VLLM_IMAGE_FETCH_TIMEOUT=60
+              pytest -s -v tests/e2e/online_serving/test_qwen_image.py -m 'core_model' --run-level 'core_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: "Diffusion · Qwen Image Layered Test"
+        commands:
+          - |
+            timeout 40m bash -c "
+              export VLLM_IMAGE_FETCH_TIMEOUT=60
+              pytest -s -v tests/e2e/online_serving/test_qwen_image_layered.py -m 'core_model' --run-level 'core_model'
+            "
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 1
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate

.buildkite/test-template-amd-omni.j2

@@ -0,0 +1,62 @@
+{# vllm-omni customized version
+   Based on: https://github.com/vllm-project/ci-infra/blob/main/buildkite/test-template-amd.j2
+   Last synced: 2025-12-15
+   Modifications: Removed unused CUDA/NVIDIA logic, keeping only AMD tests
+#}
+{% set docker_image_amd = "rocm/vllm-omni:$BUILDKITE_COMMIT" %}
+{% set default_working_dir = "/app/vllm-omni" %}
+
+  - group: "AMD Tests"
+    depends_on: ~
+    steps:
+      - label: "AMD: :docker: build image"
+        depends_on: ~
+        soft_fail: false
+        commands:
+          - "docker build -f docker/Dockerfile.rocm -t {{ docker_image_amd }} --target test --build-arg ARG_PYTORCH_ROCM_ARCH=gfx942 --progress plain ."
+          - "docker push {{ docker_image_amd }}"
+        key: "amd-build"
+        env:
+          DOCKER_BUILDKIT: "1"
+        retry:
+          automatic:
+            - exit_status: -1  # Agent was lost
+              limit: 2
+            - exit_status: -10  # Agent was lost
+              limit: 2
+            - exit_status: 128  # Git connectivity issues
+              limit: 2
+            - exit_status: 1  # Machine occasionally fail
+              limit: 1
+        agents:
+          queue: amd-cpu
+
+    {% for step in steps %}
+    {% if step.mirror_hardwares and mirror_hw in step.mirror_hardwares %}
+      - label: "{{ step.agent_pool }}: {{ step.label }}"
+        depends_on: amd-build
+        agents:
+          {% if step.agent_pool %}
+          queue: amd_{{ step.agent_pool }}
+          {% else %}
+          queue: amd_mi325_1
+          {% endif %}
+{% set cmd_body = (step.command or (step.commands | join("\n"))) | trim %}
+{% set indented_cmd = cmd_body | replace("\n", "\n            ") %}
+        command: bash .buildkite/scripts/hardware_ci/run-amd-test.sh
+        env:
+          DOCKER_BUILDKIT: "1"
+          TEST_COMMAND: |-
+            (command rocm-smi || true) && cd {{ (step.working_dir or default_working_dir) | safe }}
+{% if "mi250" in step.agent_pool %}
+            python3 -m pip uninstall -y amd-aiter
+{% endif %}
+            {{ indented_cmd | safe }}
+        priority: 100
+        {% if step.grade and step.grade == "Blocking" %}
+        soft_fail: false
+        {% else %}
+        soft_fail: true
+        {% endif%}
+    {% endif %}
+    {% endfor %}

.buildkite/test-weekly.yml

@@ -0,0 +1,148 @@
+env:
+  VLLM_WORKER_MULTIPROC_METHOD: spawn
+  VLLM_USE_FLASHINFER_MOE_FP16: 0
+  HF_HUB_DOWNLOAD_TIMEOUT: 300
+  HF_HUB_ETAG_TIMEOUT: 60
+
+steps:
+  - label: "Reliability Test - qwen3-omni"
+    timeout_in_minutes: 180
+    depends_on: upload-weekly-pipeline
+    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
+    commands:
+      - pytest -s -v tests/dfx/reliability/test_reliability_qwen3_omni.py -m "slow"
+    agents:
+      queue: "mithril-h100-pool"
+    plugins:
+      - kubernetes:
+          podSpec:
+            containers:
+              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                resources:
+                  limits:
+                    nvidia.com/gpu: 2
+                volumeMounts:
+                  - name: devshm
+                    mountPath: /dev/shm
+                  - name: hf-cache
+                    mountPath: /root/.cache/huggingface
+                env:
+                  - name: HF_HOME
+                    value: /root/.cache/huggingface
+                  - name: HF_TOKEN
+                    valueFrom:
+                      secretKeyRef:
+                        name: hf-token-secret
+                        key: token
+            nodeSelector:
+              node.kubernetes.io/instance-type: gpu-h100-sxm
+            volumes:
+              - name: devshm
+                emptyDir:
+                  medium: Memory
+              - name: hf-cache
+                hostPath:
+                  path: /mnt/hf-cache
+                  type: DirectoryOrCreate
+
+  - label: "Reliability Test - wan22"
+    timeout_in_minutes: 180
+    depends_on: upload-weekly-pipeline
+    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
+    commands:
+      - pytest -s -v tests/dfx/reliability/test_reliability_wan22.py -m "slow"
+    agents:
+      queue: "mithril-h100-pool"
+    plugins:
+      - kubernetes:
+          podSpec:
+            containers:
+              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                resources:
+                  limits:
+                    nvidia.com/gpu: 2
+                volumeMounts:
+                  - name: devshm
+                    mountPath: /dev/shm
+                  - name: hf-cache
+                    mountPath: /root/.cache/huggingface
+                env:
+                  - name: HF_HOME
+                    value: /root/.cache/huggingface
+                  - name: HF_TOKEN
+                    valueFrom:
+                      secretKeyRef:
+                        name: hf-token-secret
+                        key: token
+            nodeSelector:
+              node.kubernetes.io/instance-type: gpu-h100-sxm
+            volumes:
+              - name: devshm
+                emptyDir:
+                  medium: Memory
+              - name: hf-cache
+                hostPath:
+                  path: /mnt/hf-cache
+                  type: DirectoryOrCreate
+
+  # Invalid HTTP / WS payloads vs live Omni servers (Issue #3649 tracks known skips).
+  - group: "Reliability Test - Invalid parameters Test"
+    depends_on: upload-weekly-pipeline
+    if: build.env("WEEKLY") == "1" || build.pull_request.labels includes "weekly-test"
+    steps:
+      - label: "Invalid parameters Test · H100"
+        timeout_in_minutes: 120
+        commands:
+          - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and H100"
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 2
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      # Stable Audio Open, Qwen3-TTS speech/batch/voices paths marked ``L4``.
+      - label: "Invalid parameters Test · L4"
+        timeout_in_minutes: 120
+        commands:
+          - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and L4"
+        agents:
+          queue: "gpu_1_queue"
+        plugins:
+          - docker#v5.2.0:
+              image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              always-pull: true
+              propagate-environment: true
+              shm-size: "8gb"
+              environment:
+                - "HF_HOME=/fsx/hf_cache"
+                - "HF_TOKEN"
+              volumes:
+                - "/fsx/hf_cache:/fsx/hf_cache"

.claude/skills/add-diffusion-model/SKILL.md

@@ -24,7 +24,7 @@ Check the model's HF repo for `model_index.json`. This determines your path:
 
 | Scenario | How to identify | Migration path |
 |----------|----------------|----------------|
-| **Already supported** | `_class_name` in `model_index.json` matches a key in `_DIFFUSION_MODELS` in `registry.py` | Skip implementation, then validate model-specific examples, tests, and docs as needed |
+| **Already supported** | `_class_name` in `model_index.json` matches a key in `_DIFFUSION_MODELS` in `registry.py` | Skip to Step 5 (test) and Step 7 (docs) |
 | **Diffusers-based** | Has standard `model_index.json` with `_diffusers_version`, subfolders for `transformer/`, `vae/`, etc. | Follow **Path A** below |
 | **Custom/private repo** | No diffusers `model_index.json`, weights in non-standard format, custom model code in a separate git repo | Follow **Path B** below |
 | **Hybrid** | Has some diffusers components (VAE) but custom transformer/fusion | Mix of Path A and Path B |
@@ -52,7 +52,7 @@ vllm_omni/diffusion/models/your_model_name/
 2. Replace attention with `vllm_omni.diffusion.attention.layer.Attention` (QKV shape: `[B, seq, heads, head_dim]`).
 3. Add `od_config: OmniDiffusionConfig | None = None` to `__init__`.
 4. Add `load_weights()` method mapping diffusers weight names to vllm-omni names.
-5. Add class attributes for acceleration features such as `_repeated_blocks` and `_layerwise_offload_blocks_attrs` (see [references/transformer-adaptation.md](references/transformer-adaptation.md) for examples).
+5. Add class attributes: `_repeated_blocks`, `_layerwise_offload_blocks_attr`.
 
 ### A4. Adapt pipeline
 
@@ -78,34 +78,13 @@ class YourPipeline(nn.Module):
 
 Add post/pre-process functions in the same pipeline file. Register them in `registry.py`.
 
-### A4.1 Add progress bar support (recommended)
-
-For pipelines with a standard denoising loop, prefer the existing progress bar pattern instead of hand-rolled logging.
-
-```python
-from vllm_omni.diffusion.models.progress_bar import ProgressBarMixin
-
-class YourPipeline(nn.Module, ProgressBarMixin):
-    def forward(self, req: OmniDiffusionRequest) -> DiffusionOutput:
-        # ... prepare timesteps / latents ...
-        with self.progress_bar(total=len(timesteps)) as progress_bar:
-            for i, t in enumerate(timesteps):
-                # predict noise / scheduler step
-                latents = ...
-                progress_bar.update()
-
-        return DiffusionOutput(output=output)
-```
-
-For custom loop structures, follow `vllm_omni/diffusion/models/progress_bar.py` and existing pipelines using `ProgressBarMixin`.
-
 ### A5. Register, test, docs → continue at Step 4 below.
 
 ---
 
 ## Path B: Custom/Private Repo Model
 
-For models without a diffusers pipeline — weights in custom format, model code in a private repo. Real examples: DreamID-Omni, BAGEL, HunyuanImage3. See [references/custom-model-patterns.md](references/custom-model-patterns.md) for concrete custom-model integration patterns.
+For models without a diffusers pipeline — weights in custom format, model code in a private repo. Real examples: DreamID-Omni, BAGEL, HunyuanImage3.
 
 ### B1. Understand the reference repo
 
@@ -155,7 +134,7 @@ Copy the essential model files into `vllm_omni/diffusion/models/<name>/` and ada
 
 ### B4. Handle custom weight loading
 
-Custom models have two common patterns for weight loading:
+Custom models have two patterns for weight loading:
 
 **Pattern 1: Bypass standard loader** (DreamID-Omni style)
 
@@ -170,10 +149,8 @@ class CustomPipeline(nn.Module):
         self.vae = custom_init_vae(model, device=self.device)
         self.text_encoder = custom_init_text_encoder(model, device=self.device)
         self.transformer = CustomFusionModel(CONFIG)
-        load_custom_checkpoint(
+        load_custom_checkpoint(self.transformer,
-            self.transformer,
+            checkpoint_path=os.path.join(model, "model.safetensors"))
-            checkpoint_path=os.path.join(model, "model.safetensors"),
-        )
         # NO weights_sources defined — bypasses standard loader
 
     def load_weights(self, weights):
@@ -185,8 +162,6 @@ class CustomPipeline(nn.Module):
 When weights are in safetensors format but need name remapping:
 
 ```python
-from vllm.model_executor.model_loader.weight_utils import default_weight_loader
-
 class CustomPipeline(nn.Module):
     def __init__(self, *, od_config, prefix=""):
         super().__init__()
@@ -212,9 +187,7 @@ class CustomPipeline(nn.Module):
             # Remap original weight names to vllm-omni module names
             name = self._remap_weight_name(name)
             if name in params:
-                param = params[name]
+                default_weight_loader(params[name], tensor)
-                weight_loader = getattr(param, "weight_loader", default_weight_loader)
-                weight_loader(param, tensor)
                 loaded.add(name)
         return loaded
 ```
@@ -308,43 +281,16 @@ For Omni or custom models, create:
 ### Step 7: Update Documentation
 
 Required updates:
-1. `docs/user_guide/diffusion/parallelism/overview.md` — parallelism support overview/table
+1. `docs/user_guide/diffusion/parallelism_acceleration.md` — parallelism support table
-2. `docs/user_guide/diffusion/cpu_offload.md` — if CPU offload supported (add to supported models table)
+2. `docs/user_guide/diffusion/cpu_offload_diffusion.md` — if CPU offload supported (add to supported models table)
-3. `docs/user_guide/diffusion/cache_acceleration/teacache.md` — if TeaCache supported
+3. `docs/user_guide/diffusion/teacache.md` — if TeaCache supported
-4. `docs/user_guide/diffusion/cache_acceleration/cache_dit.md` — if Cache-DiT supported
+4. `docs/user_guide/diffusion/cache_dit_acceleration.md` — if Cache-DiT supported
-5. Offline example docs under `examples/offline_inference/<name>/` (`README.md` or category-specific `.md`)
+5. `examples/offline_inference/xxx/README.md` — offline example docs
-6. `examples/online_serving/<name>/README.md` — online serving docs
+6. `examples/online_serve/xxx/README.md` — online serve docs
 
-### Step 8: Add E2E Tests
+### Step 8: Add E2E Tests (Recommended)
 
-**Follow the [vllm-omni-test skill](../vllm-omni-test/SKILL.md)** for markers, file naming, Buildkite wiring, and run commands. Also read [l4_functionality_tests.inc.md](https://github.com/vllm-project/vllm-omni/blob/main/docs/contributing/ci/test_examples/l4_functionality_tests.inc.md), [test_system_overview.md](https://github.com/vllm-project/vllm-omni/blob/main/docs/contributing/ci/test_system_overview.md), and [test_writing_guide.md](https://github.com/vllm-project/vllm-omni/blob/main/docs/contributing/ci/test_writing_guide.md).
+Create `tests/e2e/online_serving/test_your_model_expansion.py`.
-
-Classify the model's **CI priority** first:
-
-| Priority | Required test levels | Files & markers |
-|----------|---------------------|-----------------|
-| **High** (listed in [#1832](https://github.com/vllm-project/vllm-omni/issues/1832) or on the diffusion hot path) | **L1** · **L2** online · **L3** online + offline · **L4** feature + performance | See table below |
-| **Medium** (*normal priority* in L4 docs) | **L3** online + offline · **L4** feature only | Fewer L4 parametrized rows |
-| **Low** | **L4** feature only | One or two `*_expansion.py` cases |
-
-**Per-level deliverables (diffusion / `pytest.mark.diffusion`):**
-
-| Level | Location | Marker | CI pipeline | Notes |
-|-------|----------|--------|-------------|-------|
-| **L1** | `tests/diffusion/models/{slug}/`, `tests/diffusion/cache/`, transformer unit tests | `core_model` + `cpu` | `test-ready.yml` | Weight remap, `_sp_plan`, cache enabler registration, shape contracts |
-| **L2** | `tests/e2e/online_serving/test_{slug}.py` (and offline if the category is offline-first) | **`core_model` + `advanced_model`** (both on baseline smoke) + `diffusion` + `@hardware_test` / `hardware_marks` | `test-ready.yml` | Default deploy smoke — minimal `num_inference_steps`, single prompt |
-| **L3** | `tests/e2e/online_serving/test_{slug}.py` **and** `tests/e2e/offline_inference/test_{slug}.py` when offline matters | Baseline smoke: **`core_model` + `advanced_model`**; heavier cases: `advanced_model` only (+ `diffusion`) | `test-merge.yml` **or** merged into nightly diffusion function job | Real weights, streaming/API paths, LoRA/offload smoke |
-| **L4** | `tests/e2e/online_serving/test_{slug}_expansion.py` (+ offline expansion if needed) | `full_model` + `diffusion` | `test-nightly.yml` (X2I / X2V / X2A function groups) | Feature combos per [#1832](https://github.com/vllm-project/vllm-omni/issues/1832); perf → `tests/dfx/perf/tests/test_{model}_vllm_omni.json` with per-case **`mark`** (`hardware_marks` + `full_model` + `diffusion`) |
-
-**L2 & L3 online — same file, dual marks on the baseline smoke:** The **first / simplest** case in `test_{slug}.py` (default deploy, minimal steps, single prompt) should carry **both** `@pytest.mark.core_model` and `@pytest.mark.advanced_model` on the **same** function so L2 (`test-ready.yml`) and L3 (`test-merge.yml`) share one smoke test. Heavier deploy variants or API paths in the same file use **`advanced_model` only**. When L3 moves to nightly, migrate those heavier cases into `test_{slug}_expansion.py` with `full_model` and remove the dedicated `test-merge.yml` job (see `test_longcat_image_expansion.py`, `test_qwen_image_expansion.py`).
-
-**L4 design (high priority):** Combine multiple supported features (Cache-DiT, TP, USP, CFG, HSDP, CPU offload, quantization) into **few parametrized** `OmniServerParams` rows so each feature appears in at least one case without exploding GPU jobs. Shard single-GPU vs multi-GPU cases across the nightly X2I/X2V function steps (1-GPU vs `distributed_cuda`).
-
-**L4 design (medium / low):** One or two parametrized rows covering the best quality/perf trade-off; skip perf JSON unless the model is high priority.
-
-**Reference implementations:** `tests/e2e/online_serving/test_qwen_image_edit_expansion.py`, `tests/e2e/online_serving/test_longcat_image_expansion.py`, `tests/e2e/online_serving/test_hunyuan_video_15_expansion.py`.
-
-**Keep model-specific code inside test modules — not `tests/helpers/{slug}.py`:** deploy constants, prompts, sampling dicts, and inline `request_config` / `form_data` belong in each `test_{slug}.py` and `test_{slug}_expansion.py`. Do not add per-model files under `tests/helpers/`; reuse only repo-wide harness (`mark`, `media`, `runtime`, `stage_config`, `assertions`). **L2+ online/offline e2e:** reuse or add `send_*_request` in `tests/helpers/runtime.py` — tests call the handler, not raw `omni.generate` / HTTP. See [vllm-omni-test skill](../vllm-omni-test/SKILL.md) § **Runtime send helpers**.
 
 ### Step 9: Add Cache-DiT Acceleration
 
@@ -418,8 +364,7 @@ def enable_cache_for_your_model(pipeline, cache_config):
 
 #### 9d. Register the custom enabler
 
-Add your enabler to `CUSTOM_DIT_ENABLERS` in
+Add your enabler to `CUSTOM_DIT_ENABLERS` in `vllm_omni/diffusion/cache/cache_dit_backend.py`:
-`vllm_omni/diffusion/cache/cachedit/model_specific.py`:
 
 ```python
 CUSTOM_DIT_ENABLERS = {
@@ -565,7 +510,7 @@ class YourTransformer(nn.Module):
 #### 10e. Update parallelism documentation
 
 After adding parallelism support, update:
-1. `docs/user_guide/diffusion/parallelism/overview.md` — add your model to the support overview/table
+1. `docs/user_guide/diffusion/parallelism_acceleration.md` — add your model to the support table
 2. Record which parallelism methods are supported (USP, Ring, CFG, TP, HSDP, VAE-Patch)
 
 ### Step 11: Add CPU Offload Support
@@ -623,7 +568,6 @@ See the [Profiling Single-Stage Diffusion](../../../docs/contributing/profiling.
 
 ## Reference Files
 
-- [vllm-omni-test skill](../vllm-omni-test/SKILL.md) — L1–L4 markers, naming, Buildkite wiring, run commands
 - [Transformer Adaptation](references/transformer-adaptation.md) — porting transformers from diffusers
 - [Custom Model Patterns](references/custom-model-patterns.md) — patterns for non-diffusers models
 - [Parallelism Patterns](references/parallelism-patterns.md) — TP, SP/USP, CFG parallel, HSDP implementation details

.claude/skills/add-diffusion-model/references/cache-dit-patterns.md

@@ -29,13 +29,8 @@ vLLM-Omni integrates cache-dit through `CacheDiTBackend`:
 | `cache_dit.refresh_context()` | Updates cache context when `num_inference_steps` changes |
 
 **Source files**:
-- `vllm_omni/diffusion/cache/cachedit/__init__.py` — public package API
+- `vllm_omni/diffusion/cache/cache_dit_backend.py` — `CacheDiTBackend`, enablers, `CUSTOM_DIT_ENABLERS`
-- `vllm_omni/diffusion/cache/cachedit/backend.py` — generic backend lifecycle and integration
+- `vllm_omni/diffusion/cache/` — cache backend implementations
-- `vllm_omni/diffusion/cache/cachedit/config.py` — Cache-DiT configuration types
-- `vllm_omni/diffusion/cache/cachedit/model_specific.py` — model-specific adapters, enablers, and registry
-
-Outside `vllm_omni/diffusion/cache`, import Cache-DiT symbols only from
-`vllm_omni.diffusion.cache.cachedit`.
 
 ## Standard Models: Automatic Support
 
@@ -180,8 +175,7 @@ Inspect your block's `forward()` return type and residual connection pattern to
 
 ## Registering Custom Enablers
 
-Add your enabler to `CUSTOM_DIT_ENABLERS` in
+Add your enabler to `CUSTOM_DIT_ENABLERS` in `vllm_omni/diffusion/cache/cache_dit_backend.py`:
-`vllm_omni/diffusion/cache/cachedit/model_specific.py`:
 
 ```python
 CUSTOM_DIT_ENABLERS = {
@@ -254,7 +248,7 @@ Models listed in `_NO_CACHE_ACCELERATION` in `vllm_omni/diffusion/registry.py` d
 
 | Model | Path | Notes |
 |-------|------|-------|
-| Standard DiT | `cachedit.backend::enable_cache_for_dit` | Default enabler, automatic |
+| Standard DiT | `cache_dit_backend.py::enable_cache_for_dit` | Default enabler, automatic |
-| Wan2.2 | `cachedit.model_specific::enable_cache_for_wan22` | Dual-transformer, auto-detects mode |
+| Wan2.2 | `cache_dit_backend.py::enable_cache_for_wan22` | Dual-transformer, auto-detects mode |
-| LongCat | `cachedit.config::CacheDiTAdapterConfig` | Declarative multi-block-list adapter |
+| LongCat | `cache_dit_backend.py::enable_cache_for_longcat_image` | Multi-block-list |
-| BAGEL | `cachedit.model_specific::BagelCachedAdapter` | Custom cached adapter |
+| BAGEL | `cache_dit_backend.py::enable_cache_for_bagel` | Complex omni model |

.claude/skills/add-diffusion-model/references/parallelism-patterns.md

@@ -569,4 +569,4 @@ Check which parallelism methods a model supports:
 | **TP** | Uses `ColumnParallelLinear` / `QKVParallelLinear`. Search: `grep -r 'ParallelLinear\|QKVParallel' vllm_omni/diffusion/models/<model>/` |
 | **HSDP** | Transformer defines `_hsdp_shard_conditions`. Search: `grep -r '_hsdp_shard_conditions' vllm_omni/diffusion/models/` |
 
-The canonical per-model support overview/table is in `docs/user_guide/diffusion/parallelism/overview.md`.
+The canonical per-model support table is in `docs/user_guide/diffusion/parallelism_acceleration.md`.

.claude/skills/add-diffusion-model/references/transformer-adaptation.md

@@ -219,14 +219,13 @@ def load_weights(self, weights):
 
 ### Class-Level Attributes for Features
 
-
 ```python
 class MyTransformer(nn.Module):
     # torch.compile: list block class names that repeat and can be compiled
     _repeated_blocks = ["MyTransformerBlock"]
 
     # CPU offload: attribute name of the nn.ModuleList containing blocks
-    _layerwise_offload_blocks_attrs = ["blocks"]
+    _layerwise_offload_blocks_attr = "blocks"
 
     # LoRA: mapping of fused param names to original param names
     packed_modules_mapping = {"to_qkv": ["to_q", "to_k", "to_v"]}

.claude/skills/add-tts-model/SKILL.md

@@ -220,70 +220,65 @@ See `plan/voxcpm2_native_ar_design.md`.
 
 ### Steps
 
-1. **Write one adapter** under `vllm_omni/entrypoints/openai/tts_adapters/`.
+1. **Register in `serving_speech.py`** — add all 5 points in a **single commit**;
-   `serving_speech.py` should not need an edit — detection, stage discovery and
+   partial integration causes hard-to-debug failures. This file is modified by every
-   dispatch are all derived from what the adapter declares.
+   model PR and is the most common source of rebase conflicts — see conflict note below.
 
-   Create `vllm_omni/entrypoints/openai/tts_adapters/your_model.py`:
+   **Point 1** — stage constant (near the top, alongside the other `_*_TTS_MODEL_STAGES` sets):
    ```python
-   @register_tts_adapter
+   _YOUR_MODEL_TTS_MODEL_STAGES = {"your_stage_key"}
-   class YourModelAdapter(ARTTSAdapter):
+   ```
-       name = "your_model"                              # registry key + log label
-       stage_keys = frozenset({"your_stage_key"})       # the deploy yaml's model_stage
 
-       def validate(self, request) -> str | None:
+   **Point 2** — union into `_TTS_MODEL_STAGES`:
+   ```python
+   _TTS_MODEL_STAGES: set[str] = (
+       ...
+       | _YOUR_MODEL_TTS_MODEL_STAGES
+   )
+   ```
+
+   **Point 3** — model type detection in `_detect_tts_model_type()`:
+   ```python
+   if model_stage in _YOUR_MODEL_TTS_MODEL_STAGES:
+       return "your_model"
+   ```
+
+   **Point 4** — validation dispatch in `_validate_tts_request()`:
+   ```python
+   if self._tts_model_type == "your_model":
+       return self._validate_your_model_request(request)
+   ```
+
+   **Point 5** — validation + parameter-builder methods:
+   ```python
+   def _validate_your_model_request(self, request) -> str | None:
        if not request.input or not request.input.strip():
            return "Input text cannot be empty"
        return None
 
-       async def build(self, request, sampling_params_list, has_inline_ref_audio):
+   def _build_your_model_params(self, request) -> dict:
        params = {"text": [request.input]}
        if request.voice is not None:
            params["voice"] = [request.voice]
-           return PreparedRequest(
+       return params
-               prompt={"prompt": request.input},
-               tts_params=params,
-               model_type=self.name,
-           )
    ```
+   Wire `_build_your_model_params` into `_create_tts_request()` alongside the other
+   model-specific param builders.
 
-   Then add the module to the import block at the bottom of
+   > **Two dispatch patterns coexist**: Fish Speech uses a `self._is_fish_speech` boolean
-   `tts_adapters/__init__.py` so it registers. That import line is the only shared
+   > instance attribute checked before `elif self._is_tts`, while all newer models
-   file a new model touches — which is also why the old rebase-conflict hotspot is
+   > (CosyVoice3, MOSS-TTS-Nano) use the `_tts_model_type` string returned by
-   gone.
+   > `_detect_tts_model_type()`. For new models, always use the `_tts_model_type` string
+   > pattern — do not add new `_is_*` flags.
 
-   > **Pure-diffusion TTS does not go through adapters yet.** Under
+   > **Unused variable rule**: only extract fields in `_build_your_model_params` that
-   > `for_diffusion()`, `create_speech()` routes straight to
+   > are actually forwarded to the model. Unused extractions fail `ruff F841`.
-   > `_create_diffusion_speech()` and never calls `validate()`/`build()`.
+   > For voice-cloning fields (`ref_audio` → `prompt_audio_path`, `ref_text` →
-   > `DiffusionTTSAdapter` is scaffolding with no production subclass, so logic
+   > `prompt_text`), add them to the param builder and verify they reach the model call.
-   > placed in one would silently never run. Diffusion-engine models follow the
-   > existing diffusion path; wiring it through adapters is open work (#4855).
 
-   **If a stage key alone cannot identify the model**, declare
+   **Rebase conflict note**: when rebasing onto `main` after another model was merged,
-   `model_archs = frozenset({"YourModelForConditionalGeneration"})`; add
+   `serving_speech.py` will conflict. Resolution: always keep *both* the upstream
-   `arch_identifies_entry_stage = True` when the model owns no stage key at all
+   model's additions and your own — never discard either side.
-   (Ming dense). For a rule that is not set membership, override `matches()` (see
-   `covo_audio.py`). For a genuine overlap with another adapter, give one an
-   explicit `detect_priority` — `test_tts_detection.py` fails on an unordered
-   overlap. Models that only serve speech in some topologies override
-   `stage_serves_speech()` (see `audex.py`).
-
-   **Reuse shared helpers via `self.ctx.server`** rather than reimplementing them:
-   `_resolve_ref_audio`, `_apply_uploaded_speaker`, `_validate_ref_audio_format`,
-   `_max_instructions_length`. Read a comparable adapter first — `fish_speech.py`
-   (voice cloning), `higgs_audio_v3.py` (parameter-heavy), `moss_tts.py` (family
-   sharing a base class).
-
-   > **Do not add `self._tts_model_type == ...` branches to `serving_speech.py`.**
-   > Older models predate the adapter framework and still have them; they are being
-   > migrated out (RFC #4327, #4855). `tools/pre_commit/check_tts_adapter.py` is a
-   > ratchet on the remaining count and fails the commit if it grows. Behaviour that
-   > no adapter hook can express is a missing hook — propose it on the RFC.
-
-   > **Unused variable rule**: only extract fields in `build()` that are actually
-   > forwarded to the model. Unused extractions fail `ruff F841`. For voice-cloning
-   > fields (`ref_audio` -> `prompt_audio_path`, `ref_text` -> `prompt_text`), add
-   > them to the params and verify they reach the model call.
 
 2. **Handle model-specific parameters**:
    - Voice cloning: `ref_audio` encoding and prompt injection
@@ -300,7 +295,7 @@ import base64
 from pathlib import Path
 
 def build_voice_clone_prompt(ref_audio_path: str, text: str, codec) -> list:
-    """Build prompt with reference audio for voice cloning, called from the adapter."""
+    """Build prompt with reference audio for voice cloning in serving_speech.py."""
     audio_bytes = Path(ref_audio_path).read_bytes()
     codes = codec.encode(audio_bytes)  # Encode on CPU using model's codec (e.g., DAC)
     token_ids = [code + codec.vocab_offset for code in codes.flatten().tolist()]
@@ -310,72 +305,13 @@ def build_voice_clone_prompt(ref_audio_path: str, text: str, codec) -> list:
     ]
 ```
 
-### Test Case Writing (CI Levels)
-
-**Follow the [vllm-omni-test skill](../vllm-omni-test/SKILL.md)** for markers, file naming (`test_{slug}.py` / `test_{slug}_expansion.py`), Buildkite wiring, and copy-paste run commands. Also read [test_system_overview.md](https://github.com/vllm-project/vllm-omni/blob/main/docs/contributing/ci/test_system_overview.md) and [test_writing_guide.md](https://github.com/vllm-project/vllm-omni/blob/main/docs/contributing/ci/test_writing_guide.md).
-
-Classify the model's **CI priority** first (high / medium / low). High-priority TTS models are typically those on the integration hot path or listed in tracking issues such as [#1832](https://github.com/vllm-project/vllm-omni/issues/1832); medium and low tiers cover the long tail. When unsure, ask the reviewer which tier applies.
-
-| Priority | Required test levels | Files & markers |
-|----------|---------------------|-----------------|
-| **High** | **L1** unit/logic · **L2** online smoke · **L3** online + offline integration · **L4** feature + performance | See table below |
-| **Medium** | **L3** online + offline · **L4** feature only | Skip dedicated L1/L2 unless fixing a logic bug |
-| **Low** | **L4** feature only | One or two `*_expansion.py` parametrized cases |
-
-**Per-level deliverables (TTS / `pytest.mark.tts`):**
-
-| Level | Location | Marker | CI pipeline | Notes |
-|-------|----------|--------|-------------|-------|
-| **L1** | `tests/model_executor/…`, `tests/entrypoints/openai_api/…`, stage-processor tests | `core_model` + `cpu` | `test-ready.yml` | Prompt assembly, async_chunk helpers, adapter validation — no GPU |
-| **L2** | `tests/e2e/online_serving/test_{slug}.py` | **`core_model` + `advanced_model`** (both on baseline smoke) + `tts` + `@hardware_test(...)` | `test-ready.yml` (`ready` label) | Default deploy smoke: single `/v1/audio/speech` or offline `OmniRunner` path |
-| **L3** | `tests/e2e/online_serving/test_{slug}.py` **and** `tests/e2e/offline_inference/test_{slug}.py` | Baseline smoke: **`core_model` + `advanced_model`**; heavier cases: `advanced_model` only (+ `tts`) | `test-merge.yml` **or** merged into nightly TTS function job | Streaming, voice clone, batch/queue, async_chunk |
-| **L4** | `tests/e2e/online_serving/test_{slug}_expansion.py`, optional offline expansion | `full_model` + `tts` | `test-nightly.yml` (`:full_moon: TTS · Function Test with L4`) | Feature matrix; perf → `tests/dfx/perf/tests/test_tts.json` |
-
-**L2 & L3 online — same file, dual marks on the baseline smoke:** The **first / simplest** case in `test_{slug}.py` (default deploy, single non-streaming `/v1/audio/speech` or equivalent offline path) should carry **both** `@pytest.mark.core_model` **and** `@pytest.mark.advanced_model` on the **same** function so it runs in L2 (`test-ready.yml`, `--run-level core_model`, basic validation) and L3 (`test-merge.yml`, `--run-level advanced_model`, deeper validation) without duplicating the test. In-tree examples: `test_voxcpm2_tts.py::test_text_to_audio_001`, `test_qwen3_tts_customvoice.py::test_text_to_audio_001`.
-
-Heavier scenarios in the same file use **`advanced_model` only** (streaming, extra languages, concurrency, async_chunk, batch). Example: `test_voice_clone_en_streaming_001` → `advanced_model` only. When migrating L3 to nightly, move those heavier cases into `test_{slug}_expansion.py` with `full_model` and drop the dedicated merge job (see `test_ming_tts_expansion.py`, `test_glm_tts_expansion.py`).
-
-```python
-@pytest.mark.core_model
-@pytest.mark.advanced_model
-@pytest.mark.tts
-@hardware_test(res={"cuda": "L4"}, num_cards=1)
-@pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)
-def test_voice_clone_en_non_streaming_001(omni_server, openai_client) -> None:
-    openai_client.send_audio_speech_request({...})
-```
-
-**L4 consolidation:** Prefer parametrized `OmniServerParams` rows (`default`, `async_chunk`, feature flags) in one expansion module rather than many merge-only files ([#1832](https://github.com/vllm-project/vllm-omni/issues/1832)).
-
-**L4 performance (high-priority models):** Add latency / throughput / stress rows in `tests/dfx/perf/tests/test_tts.json`, or a dedicated `tests/dfx/perf/tests/test_{slug}.json` when the model must not join the shared nightly server matrix before integration lands (see VoxCPM2 / Coqui XTTS pattern). Register the model in `benchmarks/tts/model_configs.yaml` for local `bench_tts.py`. Wire a **separate** `test-nightly.yml` Perf Test step when the JSON is not merged into `test_tts.json` yet.
-
-**Keep model-specific code inside test modules — not `tests/helpers/{slug}.py`:**
-
-- Put `MODEL`, deploy path, vendored `REF_AUDIO_URL`, `get_prompt()`, and inline `request_config` dicts **in each** `test_{slug}.py`, `test_{slug}_expansion.py`, offline `test_{slug}.py`, and L1 `test_{slug}_*.py` as needed.
-- **Do not** add `tests/helpers/{slug}.py` (or `tests/helpers/{model_name}.py`) to deduplicate constants or request builders across those files. A little duplication is intentional; follow in-tree references such as `tests/e2e/online_serving/test_glm_tts.py` and `tests/e2e/online_serving/test_cosyvoice3_tts_expansion.py`.
-- `tests/helpers/` is for **repo-wide** harness code only (`mark.py`, `media.py`, `runtime.py`, `stage_config.py`, `assertions.py`, `fixtures/`). Import those; do not extend the tree with per-model modules.
-
-**Runtime send helpers (`tests/helpers/runtime.py`) — online and offline e2e:**
-
-| Path | Fixture | Call |
-|------|---------|------|
-| Online `/v1/*` | `openai_client` | `openai_client.send_*_request(request_config)` |
-| Offline inference | `omni_runner_handler` | `omni_runner_handler.send_*_request(request_config)` |
-
-1. **Grep `runtime.py` first** — reuse `send_omni_request`, `send_diffusion_request`, `send_audio_speech_request` (online + offline Qwen-style TTS), `send_single_stage_tts_request` (Coqui XTTS / MOSS-TTS-Nano offline), etc.
-2. **No matching helper** → add `send_<feature>_request` (or `send_<route>_http_request` for negative/dfx) in **`runtime.py`** with general `assert_*` bundled inside, **then** call it from the test.
-3. **Test file** holds `request_config` dicts only — not `omni.generate`, not `_collect_audio()`, not raw HTTP/SDK.
-4. Wire `tests/helpers/runtime.py` into Buildkite `source_file_dependencies` when you add helpers.
-
-See [vllm-omni-test skill](../vllm-omni-test/SKILL.md) § **Runtime send helpers** for full tables and exceptions.
-
 ### Deliverables
 
-- One adapter file under `tts_adapters/` plus its line in the package import block
+- Updated `serving_speech.py` with all 5 integration points (single commit)
 - Client scripts and server launcher under `examples/online_serving/text_to_speech/<model>/`
 - Gradio demo with streaming and voice cloning UI in the same dir
-- E2E tests per **Test Case Writing (CI Levels)** above (priority tier determines L1–L4 scope)
+- E2E online serving test (`tests/e2e/online_serving/test_<model>.py`)
-- Buildkite wired per level: `test-ready.yml` (L1/L2), `test-merge.yml` or nightly function job (L3), `test-nightly.yml` (L4) — see [vllm-omni-test skill](../vllm-omni-test/SKILL.md)
+- Buildkite CI entry in `.buildkite/test-merge.yml`
 - New section in `examples/online_serving/text_to_speech/README.md` (table row + per-model section). Do **not** create a top-level `examples/online_serving/<model>/` dir or a per-model `README.md` inside `text_to_speech/<model>/`.
 
 ### E2E test pitfalls to avoid
@@ -390,9 +326,9 @@ See [vllm-omni-test skill](../vllm-omni-test/SKILL.md) § **Runtime send helpers
 - **Use the harness readiness gate.** The fixture waits for HTTP 200 on
   `/health`; don't add `time.sleep` in tests. If warmup is incomplete, make
   `/health` return non-200 until you're actually ready.
-- **Mark tests per the CI Levels table** — baseline smoke: `core_model` + `advanced_model`; heavier cases: `advanced_model` only; L4 expansion: `full_model`
+- **Mark with `@pytest.mark.core_model` + `hardware_test(res={"cuda": "H100"})`**
-- **No per-model helper modules** — do not create `tests/helpers/{slug}.py`; keep constants and `request_config` payloads in the test file
+  so the test lands in `test-ready.yml` (triggered by the `ready` label) rather
-- **Online and offline e2e go through `runtime.py`** — `openai_client.send_audio_speech_request` (online); `omni_runner_handler.send_audio_speech_request` (Qwen-style offline) or `send_single_stage_tts_request` (single-stage offline). Add a new `send_*_request` in `runtime.py` when none fits; do not embed `omni.generate` or HTTP in tests
+  than only nightly.
 
 ## Phase 4: Async Chunk (Streaming)
 
@@ -519,14 +455,14 @@ Use this checklist when integrating a new TTS model:
 - [ ] README.md written
 
 ### Phase 3: Online Serving
-- [ ] Adapter written under `tts_adapters/` and registered in the import block
+- [ ] All 5 `serving_speech.py` integration points added in one commit
-- [ ] Only extract params in `build()` that are forwarded to the model call (ruff F841)
+- [ ] Only extract params in `_build_*_params` that are forwarded to the model call (ruff F841)
 - [ ] Prompt builder handles text input correctly
 - [ ] Voice cloning works (if supported)
 - [ ] All response formats work (wav, mp3, flac, pcm)
 - [ ] Client scripts and server launcher created
-- [ ] E2E tests added per model priority tier (see **Test Case Writing (CI Levels)**)
+- [ ] E2E online serving test written (`tests/e2e/online_serving/test_<model>.py`)
-- [ ] Buildkite entries match level: `test-ready.yml` / `test-merge.yml` or nightly TTS job / `test-nightly.yml`
+- [ ] Buildkite CI entry added to `.buildkite/test-merge.yml`
 - [ ] Gradio demo working
 - [ ] Documentation added (offline + online docs, nav, supported models)
 
@@ -564,6 +500,5 @@ Project docs and adjacent skills:
 - [TTS audio skill](../vllm-omni-audio-tts/SKILL.md) — supported models and usage
 - [Fish Speech integration](../vllm-omni-audio-tts/references/fish-speech.md) — complete example of Phases 1–3
 - [Qwen3-TTS reference](../vllm-omni-audio-tts/references/qwen-tts.md) — complete example of all 5 phases
-- [vllm-omni-test skill](../vllm-omni-test/SKILL.md) — L1–L4 markers, naming, Buildkite wiring, run commands
 - [Adding a TTS model (developer guide)](https://github.com/vllm-project/vllm-omni/blob/main/docs/contributing/model/adding_tts_model.md)
 - `plan/voxcpm2_native_ar_design.md` — VoxCPM2's vLLM-native AR + side-computation pattern (distinct from the generator-based single-stage described above)

.claude/skills/diffusion-perf-opt/SKILL.md

@@ -21,9 +21,6 @@ Before proposing changes, ask for the optimization scene if it is not already kn
 - Current enabled strategies: USP/SP, CFG parallel, HSDP/FSDP, VAE patch parallel, torch.compile, profiler options.
 - Optimization target: latency, throughput, memory, cost, or quality-preserving speed.
 - Precision/quality tolerance: bf16/fp8/quantization/sparsity/approximate attention allowed or not.
-- Quality validation method: exact-output comparison when feasible, or metrics
-  such as SSIM, PSNR, LPIPS, cosine similarity, MAE, MSE, temporal flicker
-  checks, baseline self-run variance, and reviewable output artifacts.
 
 ## Workflow
 
@@ -82,19 +79,7 @@ Before proposing changes, ask for the optimization scene if it is not already kn
    - Record latency, stage timings, memory, output quality, and logs.
    - Report comparison tables in ms. Include at least end-to-end client time, server `inference_time`, server stage generation time if available, `vae.encode`, `diffuse`, `vae.decode`, and peak memory.
 
-6. **Enforce the quality and precision gate for every optimization.**
+6. **Collect diagnostic trace only after narrowing hypotheses.**
-   - Do not mark an optimization ready until quality is checked on the same
-     workload: model, prompt/media, seed, shape, steps, scheduler, dtype,
-     backend, parallelism, and output encoding.
-   - For math-preserving changes, require exact/near-exact agreement or show
-     that differences are within baseline self-run variance.
-   - For precision, quantization, approximate attention, sparse/custom kernels,
-     or backend changes, include reviewable artifacts and metrics such as SSIM,
-     PSNR, LPIPS, cosine similarity, MAE, MSE, and temporal flicker checks.
-   - If quality tolerance is not stated, default to quality-preserving behavior.
-     Failed or inconclusive quality validation blocks a ready-to-merge claim.
-
-7. **Collect diagnostic trace only after narrowing hypotheses.**
    - Use torch profiler for a small number of requests.
    - Run two separate diagnostic traces instead of mixing concerns:
      - **Operator/shape trace**: enable `torch_profiler_record_shapes=True` and keep stack collection disabled. Use this to rank CUDA kernels, NCCL collectives, attention/MLP/norm/RoPE work, and shape-specific hot operators.
@@ -106,16 +91,15 @@ Before proposing changes, ask for the optimization scene if it is not already kn
    - Diagnostic reports must be written to disk and preserve: server command, profiler config, warmup/request/polling commands, trace artifact paths, rank analyzed, analyzer output or summary, and the decision about whether additional ranks are necessary.
    - Analyze both rank-level balance and device-level free bubbles when additional ranks are opened.
 
-8. **Analyze host, communication, and operators.**
+7. **Analyze host, communication, and operators.**
    - Find GPU idle/free intervals and map each large gap to the enclosing CPU/Python code.
    - Separate real GPU idle from profiler overhead such as CUPTI `Command Buffer Full`.
    - Compare NCCL kernel time to user annotations; annotations can overcount nested intervals.
    - Rank operator work by total CUDA time and by repeated small-kernel launch count.
 
-9. **Produce an optimization plan.**
+8. **Produce an optimization plan.**
    - Classify candidates as P0/P1/P2.
    - For each candidate, state necessity, expected benefit, implementation path, validation plan, and quality risk.
-   - Include a concrete quality/precision validation gate for each candidate.
    - Do not implement high-risk operator rewrites before proving the operator is a bottleneck for the target shapes.
    - End the plan with a user-facing candidate selection table. The assistant
      should not automatically choose a risky optimization just because it is
@@ -140,13 +124,7 @@ Before proposing changes, ask for the optimization scene if it is not already kn
 - **P1:** meaningful code changes with contained risk. Examples: cross-attention KV caching, VAE gather/broadcast reduction, AdaLayerNorm/RMSNorm/RoPE fusion after trace evidence.
 - **P2:** high implementation or quality risk. Examples: FA to LA replacement, custom Triton/CUDA fused kernels, FP8/quantization, sparsity/Rainfusion-style acceleration.
 
-Every implemented optimization needs A/B validation and a passing
+Every implemented optimization needs A/B validation and quality regression. A/B means same workload and hardware before/after. Quality regression means checking generated image/video stability, artifacts, temporal flicker, and seed behavior when precision or approximate kernels change.
-quality/precision gate, including math-preserving changes such as padding trim,
-layout cleanup, cache reuse, or host/runtime cleanup. Use objective metrics
-when available, keep reviewable artifacts, and compare against baseline
-self-run variance for precision, quantization, approximate kernels, or backend
-changes. If quality validation fails or is inconclusive, do not present the
-optimization as ready to merge.
 
 ## Optimization Layers
 

.claude/skills/precheck-pr/SKILL.md

@@ -1,103 +0,0 @@
----
-name: precheck-pr
-description: Self-check your branch before creating a PR — catch dead code, prevent new model-specific Python examples, verify accuracy/perf claims, validate PR title format, and confirm merge readiness. Use when the user says "precheck", "self review", "pre-submit check", or "check my PR before I open it." Never posts to GitHub.
----
-
-# PR Pre-Check
-
-Self-review your branch before creating a PR against `vllm-project/vllm-omni`. Two modes: **quick** catches showstoppers, **full** does a thorough maintainer-grade review. Never posts to GitHub; the report is for the contributor's terminal only.
-
-## Mode Selection
-
-| Mode | When | Time |
-|------|------|------|
-| **Quick** | About to push, final sanity check | ~3 min |
-| **Full** | Ready for review, want maintainer-level scan | ~10 min |
-
-Default to quick if unsure. Run full before marking a PR "ready for review."
-
-## Workflow
-
-### Step 1: Detect Base Branch
-
-```bash
-BASE_SHA=$(git merge-base HEAD origin/main 2>/dev/null \
-         || git merge-base HEAD main 2>/dev/null \
-         || echo origin/main)
-echo "diffing against ${BASE_SHA}"
-git diff --name-only ${BASE_SHA}...HEAD
-```
-
-### Step 2: Validate PR Title
-
-Check the most recent commit message (or branch name if no commit yet) against the project convention. Valid prefixes:
-
-| Prefix | Applies to |
-|--------|-----------|
-| `[Bugfix]` | Bug fixes |
-| `[CI/Build]` | Build or CI improvements |
-| `[Doc]` | Documentation changes |
-| `[Model]` | New/improved models (include model name) |
-| `[Frontend]` | Frontend changes (API server, OmniLLM class, etc.) |
-| `[Kernel]` | CUDA/kernel changes |
-| `[Core]` | Core logic changes (OmniProcessor, OmniARScheduler, etc.) |
-| `[Hardware][Vendor]` | Hardware-specific (e.g., `[Hardware][Ascend]`) |
-| `[Misc]` | Other changes (use sparingly) |
-
-✗ if: missing prefix, wrong case (`[bugfix]`), or WIP/Draft in title.
-⚠ if: `[Model]` prefix without the model identifier (e.g., `[Model] Add new model` — should be `[Model] Add <ModelName> ...`).
-
-### Step 3: Categorize the PR
-
-| Diff contains | PR type |
-|---------------|---------|
-| New files under `vllm_omni/model_executor/models/<name>/` | **New Model** |
-| Changes to `vllm_omni/diffusion/` | **Diffusion Model** |
-| `[Bugfix]` prefix or single-file fix | **Bug Fix** |
-| Perf/benchmark/throughput claims in commit msg or diff | **Performance** |
-| Everything else | **General** |
-
-If multiple rows apply (e.g., a diffusion model is also a new model), union the checklists.
-
-### Step 4: Run Checklist
-
-Ask: "Quick mode or full mode?" Then walk the checklist for the detected PR type from [references/checklists.md](references/checklists.md). Each item produces ✓, ✗, or ⚠.
-
-**Also run the Code-Quality sweep on every PR**, regardless of type or mode: the five diff-scoped checks in [references/code-quality.md](references/code-quality.md) — kwargs fragility, broad-except swallow, `Any`/wrong type hints, hot-path `.clone()`/`deepcopy`, and event-loop blocking — plus the advisory conventions (log level, structured logging, synchronization, cleanup, dependencies, naming) in [checklists.md](references/checklists.md). These count only lines the PR *adds* — the pre-existing backlog across the repo is out of scope.
-
-**Also run the Examples-Policy check on every PR** using [references/examples-policy.md](references/examples-policy.md). Inspect only Python paths introduced by the diff. Treat a new model-, checkpoint-, vendor-, or family-specific Python example as blocking; do not report pre-existing example debt.
-
-### Step 5: Print Report
-
-```
-Pre-check report for <branch>
-
-  Mode: quick | full
-  Type: <new-model | diffusion-model | bug-fix | perf | general>
-
-  Dimension          Result
-  ─────────────────  ──────
-  PR title format    ✓
-  Code quality       ⚠ 1 broad except, 2 Any hints
-  Examples policy    ✗ new model-specific Python example
-  PR desc integrity  ✓
-  Registry/config    ✓
-  Dead code          ⚠ 2 warnings
-  Accuracy           ✓
-  Benchmark          ✗ missing software versions
-
-  Verdict: 1 blocking | 2 warnings | recommend fixing ✗ before PR
-```
-
-**Severity:**
-
-| Mark | Meaning |
-|------|---------|
-| ✗ | Blocking — fix before opening PR |
-| ⚠ | Warning — consider fixing |
-| ✓ | Pass |
-| — | Skipped (not applicable) |
-
-### Stop Here
-
-Do not post comments, open PRs, or modify files. The report is for the contributor's terminal only.

.claude/skills/precheck-pr/references/checklists.md

@@ -1,173 +0,0 @@
-# Pre-Check Checklists
-
-Each item is a concrete check to run against the diff. ✗ = fix before PR. ⚠ = consider fixing.
-
----
-
-## All PRs: Title Format (check first)
-
-PR title must follow the project convention documented in `docs/contributing/README.md`:
-
-| Prefix | Applies to |
-|--------|-----------|
-| `[Bugfix]` | Bug fixes |
-| `[CI/Build]` | Build or CI improvements |
-| `[Doc]` | Documentation changes |
-| `[Model]` | New/improved models (include model name) |
-| `[Frontend]` | Frontend changes (API server, OmniLLM class, etc.) |
-| `[Kernel]` | CUDA/kernel changes |
-| `[Core]` | Core logic changes (OmniProcessor, OmniARScheduler, etc.) |
-| `[Hardware][Vendor]` | Hardware-specific (e.g., `[Hardware][Ascend]`) |
-| `[Misc]` | Other changes (use sparingly) |
-
-**Examples:**
-```
-✓ [Model] Add MiniCPM-o 4.5 support
-✓ [Bugfix] Fix Ovis image text encoder dtype
-✓ [Core] Qwen3-Omni performance optimization
-✓ [Hardware][Ascend] Fix VoxCPM2 on Ascend
-✗ Fix Ovis image text encoder dtype              ← missing prefix
-✗ [bugfix] Fix Ovis image text encoder           ← wrong case
-✗ [WIP] Add model                                ← WIP in title
-```
-
-- [ ] **Title has valid prefix** — ✗ if missing prefix, wrong case, or WIP/Draft in title. For `[Model]` PRs, the title MUST also include the model identifier (e.g., `[Model] Add <ModelName> ...`). ⚠ if missing the model name.
-
----
-
-## All PRs: Code Quality (run on every PR, quick & full)
-
-Diff-scoped sweep for five fragility patterns that are pervasive in the existing codebase — **only lines the PR adds count**, not the pre-existing backlog. Detection commands, codebase examples, and full severity rules live in [code-quality.md](code-quality.md).
-
-- [ ] **No new `**kwargs` string-lookup plumbing:** the diff adds no `**kwargs` + `kwargs["..."]` / `kwargs.get("...")` / `"..." in kwargs`. ⚠ any new instance; ✗ if a new string key is duplicated across ≥2 files without a shared constant, or unknown keys are silently dropped on a fail-fast path.
-- [ ] **No new broad exception swallow:** the diff adds no `except Exception:` / bare `except:`. ⚠ any new instance; ✗ for `except: pass` / `except Exception: return None` / `continue` on a fail-fast path (init, config validation, weight loading, request handling).
-- [ ] **No new `Any` / wrong type hints:** the diff adds no `: Any` / `-> Any` / untyped production signature, and no new `SimpleNamespace` in tests faking an object that already has a real typed stub. ⚠ any new instance; ✗ for a *wrong* (actively misleading) annotation or a `SimpleNamespace` test fake of a typed object.
-- [ ] **No new hot-path copy:** the diff adds no `.clone()` / `.copy_()` / `copy.deepcopy(...)` inside a per-step loop or per-request path. ⚠ any new instance; ✗ for `.clone()` of a full latent/activations tensor inside an AR or diffusion step loop without a comment, or `deepcopy` of a scheduler / sampling-config on the request path.
-- [ ] **No new event-loop blocking:** the diff adds no `time.sleep` / blocking HTTP (`requests`, `urllib`) / `await` inside a held lock in `async def` code. ⚠ any new instance; ✗ for blocking sleep or HTTP on the serving path (`engine/`, `entrypoints/`, async `connectors/`), or a lock held across an `await`. Blocking inside a dedicated worker thread is fine.
-
-Roll the ⚠/✗ counts into the report as a single **Code quality** dimension row.
-
----
-
-## All PRs: Examples Policy (run on every PR, quick & full)
-
-Inspect Python files introduced under `examples/` using
-[examples-policy.md](examples-policy.md). This is a diff-scoped ratchet: existing
-model-specific examples may be edited or removed without triggering the check.
-
-- [ ] **No new model-specific Python examples:** the diff adds, copies, or renames no Python file whose path or behavior is specific to one model, checkpoint, vendor, or model family. ✗ for any violation. Route inference through a shared task/protocol entrypoint, model request behavior through `vllm_omni/model_extras`, and commands through task docs or `recipes/`.
-- [ ] **New generic example code is justified:** any new task-neutral Python file under `examples/` is an actual user-facing entrypoint rather than reusable production logic, a benchmark, an app, a setup tool, or a reproducer. ⚠ when the placement is questionable.
-
-Roll the result into the report as a separate **Examples policy** dimension.
-
-### Conventions (eyeball — no grep)
-
-Judgment calls that don't grep cleanly — apply them while reading the diff, not as a mechanical check:
-
-- **Right log level** — `info` is for end-user-visible events; routine internal events are `debug`; hot paths are `trace` or removed. Logging is not free.
-- **Structured fields over f-strings** — pass dynamic values as structured fields (`logger.info("msg", extra={...})`), not interpolated strings, so they stay greppable and parseable.
-- **No reflexive synchronization** — don't add `threading.Lock` / `asyncio.Lock` / `deepcopy` / re-wrap shared state unless there is real concurrent mutation; the GIL covers most Python code. Owners decide their own synchronization — don't pre-lock in a constructor.
-- **Context managers for cleanup** — use `with` / `contextlib` for files, locks, CUDA streams, and profilers; not raw `open()` + manual `.close()` or ad-hoc `finally`.
-- **No new dependencies without justification** — prefer the stdlib and existing vllm-omni deps; a new top-level dep needs a reason (check `pyproject.toml` / `requirements*.txt`).
-- **Naming / interface discipline** — don't rename or change interfaces just for taste in this PR, but do fix names that actively mislead (e.g. `serve` implying a long-running server, `Instance` where multiple instance kinds coexist).
-
----
-
-## Bug Fix PRs
-
-### Quick
-
-- [ ] **PR body has 4 sections:** what broke (error message), repro steps, root cause, fix description
-- [ ] **Fix is minimal:** diff touches only files directly related to the bug. No unrelated refactors or style changes.
-- [ ] **Repro is runnable:** the PR body includes a copy-paste command that reproduces the bug
-- [ ] **Branch is rebased:** `git merge-base HEAD origin/main` is recent, no merge conflicts
-
-### Full (adds)
-
-- [ ] **Regression test exists:** `git diff --name-only` includes at least one `tests/` file
-- [ ] **Regression test reproduces the original error:** the test would fail on main, pass on this branch
-- [ ] **Fix matches root cause exactly:** no "fix the symptom + something else" — if the root cause is dtype, the fix is dtype, not dtype + reformatting
-- [ ] **No silent failure risk:** no bare `except: pass`, no `try: ... except: return None`, no empty fallback added. See the broad-except pattern in [code-quality.md](code-quality.md#2-broad-exception-swallow) for the full severity rule (⚠ any new broad catch; ✗ for a swallow on a fail-fast path).
-- [ ] **Upstream pattern match:** the fix follows the same pattern as existing code for similar cases (grep for analogous `from_pretrained` calls, etc.)
-- [ ] **Environment documented:** torch/transformers/vllm versions listed if the bug is version-dependent
-
----
-
-## Performance PRs
-
-### Quick
-
-- [ ] **Before/after numbers in PR body:** at minimum, one metric (RTF, RPS, latency, VRAM) with main vs PR values
-- [ ] **Hardware specified:** GPU model, count, VRAM. "L4" or "H20" is sufficient. "tested on GPU" is not.
-- [ ] **Concurrency scaling:** if the optimization claims better throughput, numbers at 2+ concurrency levels
-- [ ] **No unexplained regressions:** if any metric goes down at any concurrency level, explain why
-- [ ] **Branch is rebased:** `git merge-base HEAD origin/main` is recent, no merge conflicts
-
-### Full (adds)
-
-- [ ] **Software versions:** torch, CUDA, vllm, vllm-omni versions in PR body
-- [ ] **Warmup stated:** "1 warmup + 3 measured" or equivalent
-- [ ] **Stddev or range:** not just a single best run. "average of 2 rounds" is minimum.
-- [ ] **VRAM measured:** peak GPU memory before and after
-- [ ] **Benchmark script checked in:** under `tests/` or `examples/`, runnable by reviewer
-- [ ] **Exact command line in PR:** not pseudocode, not "run the benchmark"
-- [ ] **Pytest summary included:** `36 passed, 3 skipped, 17 warnings in 2897.66s` — proves the whole suite passes
-- [ ] **Config changes documented:** if `max_num_seqs`, `gpu_memory_utilization`, or deploy YAML changed, old and new values stated with reasoning
-
----
-
-## New Model PRs
-
-### Quick
-
-- [ ] **PR body file list matches `git diff --name-only`:** every file path in the description exists in the diff
-- [ ] **Registry entries match claimed count:** count `_OMNI_MODELS` or `_DIFFUSION_MODELS` entries added vs claimed in body
-- [ ] **Pipeline config `custom_process_input_func` paths resolve:** each referenced module.function exists
-- [ ] **`__init__.py` exports match registry:** each registered class appears in `__init__.py` and `__all__`
-- [ ] **Shell script modes match README:** `run_curl.sh` supports every mode the README documents
-- [ ] **Branch is rebased:** `git merge-base HEAD origin/main` is recent, no merge conflicts
-
-### Full (adds)
-
-- [ ] **Dead code scan (5 patterns):**
-  1. Dead `forward()` — defined but never called through the pipeline path
-  2. Dead factory/builder functions — instantiated nowhere
-  3. Dead wrappers — thin wrappers with no callers
-  4. Dead branch guards — `if version > X` where X is always satisfied
-  5. Unused parameters — `__init__` args never accessed
-- [ ] **Copy-paste detection:** no string constant defined in 3+ files, no cross-module validation duplication, no near-identical shape coercion fns
-- [ ] **Import hygiene:** no re-export-only imports, no module-level side effects without docs, no `import os` in function body when already at top. Function-body imports are acceptable when the import is only reachable from a closure or factory return value (i.e., `import` would otherwise execute at module load even though the user may never trigger that path). Either lift to top-of-file or annotate with `# noqa: PLC0415`.
-- [ ] **Accuracy:** at least one test compares output against reference; audio = valid WAV at correct sample rate; determinism verified if seed claimed. ⚠ if missing and not explicitly deferred to a follow-up PR or RFC section; — if explicitly deferred (the deferral target SHOULD be linked in the PR body).
-- [ ] **Performance:** hardware, software versions, warmup, and metrics (RTF, VRAM, RPS, latency) stated. ⚠ if missing and not explicitly deferred; — if explicitly deferred.
-- [ ] **Benchmark settings:** model config (TP, PP, max_model_len, enforce_eager, quant), runtime config (batch, input/output spec), environment versions
-- [ ] **Benchmark script checked in + exact command line + pytest summary**
-
----
-
-## Diffusion Model PRs
-
-Diffusion models live under `vllm_omni/diffusion/`. In addition to the New Model checklist above, verify:
-
-- [ ] **Transformer adapter follows contract:** inherits from `nn.Module`, implements `load_weights()`, uses `vllm_omni.diffusion.attention.layer.Attention`
-- [ ] **Pipeline has both offline and online paths:** `forward()` for batch generation, streaming path for online serving
-- [ ] **Cache-DiT integration:** at least one acceleration (TeaCache, FBCache, etc.) is wired up. ✗ for new **top-level** pipelines. For **subclass** pipelines that inherit `__call__` from a parent where Cache-DiT is already absent, downgrade to ⚠ and recommend filing a follow-up issue against the parent pipeline family.
-- [ ] **Parallelism config:** TP/SP/USP/CFG-Parallel options exposed in pipeline config
-- [ ] **Docs table updated:** model added to `docs/models/supported_models.md` with correct metadata
-- [ ] **E2E test exists:** at least one test exercises the full generate path
-
----
-
-## General PRs
-
-### Quick
-
-- [ ] **PR body matches diff:** description doesn't claim changes not in the diff
-- [ ] **Branch is rebased:** `git merge-base HEAD origin/main` is recent, no merge conflicts
-- [ ] **CI gates passing:** DCO, pre-commit, build — check `gh pr view --json statusCheckRollup` if a PR already exists
-
-### Full (adds)
-
-- [ ] **No new dead code in changed files:** scan for unreachable paths, unused imports
-- [ ] **Test coverage:** if core code changed (`engine/`, `stages/`, `connectors/`), tests are added or existing tests cover the path
-- [ ] **Import hygiene:** no redundant imports added
-- [ ] **No unrelated changes:** diff scope matches PR description

.claude/skills/precheck-pr/references/code-quality.md

@@ -1,179 +0,0 @@
-# Code-Quality Patterns
-
-Five fragility patterns to sweep on **every** PR, in both quick and full mode. These are pervasive in the existing codebase (hundreds of pre-existing sites) — so the checks are **diff-scoped**: only lines the PR *adds* count. Whole-repo greps light up every PR with the backlog and are useless.
-
-All commands assume:
-```bash
-BASE="$(git merge-base HEAD origin/main)"
-```
-
-**Severity:** ⚠ for any *new* instance introduced by the diff; ✗ for the acute sub-cases defined per pattern. Acute ✗ findings belong in the report's blocking count.
-
----
-
-## 1. `**kwargs` string-lookup passthrough
-
-### Anti-pattern
-```python
-def forward(self, **kwargs):
-    # BLOCKER-prone: raw dict + string keys duplicated across files
-    if "runtime_additional_information" in kwargs and \
-       "model_intermediate_buffer" not in kwargs:
-        ...
-```
-Real instances of this exact guard are copy-pasted across `cosyvoice3.py`, `indextts2_talker.py` (×2), `indextts2_s2mel_decoder.py`, `qwen3_tts_talker.py`, `qwen3_omni.py`. A typo in any string key silently no-ops; there is no type check, no IDE completion, and unknown keys are silently dropped.
-
-### Why dangerous
-Raw `dict` + `**kwargs` + lists of param-name strings is **fragile by construction**: the compiler can't see a missing or misspelled key, so failures are silent. Each duplicated copy is a new place for the strings to drift.
-
-### Severity
-- ⚠ any *new* `**kwargs` signature whose body does `kwargs["..."]` / `kwargs.get("...")` / `"..." in kwargs`.
-- ✗ when the diff introduces a **new** string key that is duplicated across ≥2 files without a shared module constant, or when `**kwargs` plumbing **silently drops unknown keys** on a fail-fast path (init, config validation, weight loading).
-
-### Detect (diff-scoped)
-```bash
-git diff ${BASE}...HEAD -- "*.py" | grep "^+[^+]" \
-  | grep -E '\*\*kwargs|kwargs(\.get|\[)|"[a-z_]+"\s+in\s+kwargs'
-```
-
-### Fix
-Prefer explicit typed params. The repo already has the right primitive: `msgspec.Struct` with `forbid_unknown_fields=True` rejects unknown keys instead of silently dropping them — see `_StructBase` in `vllm_omni/data_entry_keys.py:105` and `MoriPullRequest` in `vllm_omni/distributed/omni_connectors/connectors/mori_transfer_engine_connector.py:81`. A `@dataclass` or `TypedDict` works too.
-
-If `**kwargs` is unavoidable (vLLM base-class compat), centralize the key strings as module-level constants behind **one** typed accessor, instead of repeating the literal across files.
-
----
-
-## 2. Broad exception swallow
-
-### Anti-pattern
-```python
-# BLOCKER-prone: catches everything, returns None on any failure
-try:
-    evt = build_event(...)
-    return evt
-except Exception:
-    return None
-```
-Real clusters: `vllm_omni/metrics/stats.py:240,274,367,450` and `vllm_omni/metrics/{modality,utils}.py` — all `except Exception: return None`.
-
-### Why dangerous
-A generic `except Exception:` is **too flexible**. If we catch an exception type we don't expect, it is almost always an unhandled edge case that needs to be *fixed* — not swallowed into `None`/`pass`/`continue`. Broad catches turn fixable bugs into silent wrong behavior and make debugging impossible.
-
-The repo backs this with ruff `BLE001` (broad-exception catch); it is currently suppressed via `# noqa: BLE001` in `vllm_omni/patch.py:413`. Prefer fixing over suppressing.
-
-### Severity
-- ⚠ any *new* `except Exception:` / `except BaseException:` / bare `except:`.
-- ✗ for `except:` / `except Exception: pass|return None|continue` on a **fail-fast path** (init, config validation, weight loading, request handling, connector setup). This extends the Bug-Fix "No silent failure risk" ✗ in [checklists.md](checklists.md).
-
-### Detect (diff-scoped)
-```bash
-# Any new broad catch (⚠ baseline):
-git diff ${BASE}...HEAD -- "*.py" | grep "^+[^+]" \
-  | grep -E 'except\s*(Exception|BaseException)?\s*:'
-# Note: this matches only the immediate-colon swallow forms (`except :`,
-# `except Exception:`) — it deliberately excludes specific catches like
-# `except ValueError:` and the `except Exception as e:` variant. Eyeball
-# the latter; `as e` usually means it is logged, but still verify.
-```
-
-### Fix
-Catch the **specific** types you actually expect (`ValueError`, `KeyError`, `AttributeError`, `OSError`, `torch.cuda.OutOfMemoryError`, `msgspec.ValidationError`, …). At a genuine top-level / best-effort boundary (metrics, signal handlers), at minimum **log** the exception; never swallow into a bare `pass`/`return None` on a path that should fail loudly.
-
----
-
-## 3. `Any` / wrong type annotations
-
-### Anti-pattern
-```python
-# ⚠ Any param + Any return — no contract, no narrowing
-def _extract_mm_output(engine_outputs: Any) -> dict[str, Any]:
-    ...
-```
-
-### Why dangerous (root cause)
-`Any` disables the type checker for that position, so typos and wrong shapes pass silently. The repo has 636 `: Any` params, 244 `-> Any` returns, and **1,173 `SimpleNamespace` in `tests/`**. The `Any` leak is largely test-driven: vibe-coded unit tests fake objects with `SimpleNamespace`, which forces the production code consuming them to be typed `Any`, and the `Any` then propagates outward into public signatures.
-
-### Severity
-- ⚠ any *new* `: Any` / `-> Any` / fully-untyped signature in production code.
-- ✗ for a **wrong** annotation (actively misleading — e.g. `-> bool` that returns `Optional[bool]`), or a *new* `SimpleNamespace` in a test that mimics an object which already has a real typed stub / `@dataclass` / `TypedDict` / `Protocol`.
-
-### Detect (diff-scoped)
-```bash
-# Any leaking into new signatures:
-git diff ${BASE}...HEAD -- "*.py" | grep "^+[^+]" \
-  | grep -E ':\s*Any\b|->\s*Any\b'
-# SimpleNamespace newly added in tests (the Any-leak source):
-git diff ${BASE}...HEAD -- "tests/" | grep "^+[^+]" | grep "SimpleNamespace"
-```
-
-### Fix
-Replace `Any` with the concrete type, a `Protocol`, or a `Union`. If a type is genuinely dynamic, prefer `object` + `isinstance` narrowing over `Any` — `object` keeps the checker engaged. In tests, replace `SimpleNamespace` with the real class, a small `@dataclass`/`TypedDict`, or a `Protocol` + fake, so the system under test stays fully typed.
-
----
-
-## 4. Unnecessary copy — `.clone()` / `copy.deepcopy` in hot paths
-
-### Anti-pattern
-```python
-# Per-step in a diffusion/AR loop: clones the full latent every iteration
-for t in timesteps:
-    trajectory_latents.append(x_t.clone())   # O(N) GPU alloc + memcpy each step
-```
-Real clusters: `vllm_omni/diffusion/models/bagel/bagel_transformer.py` calls `x_t.clone()` ~9× across a trajectory loop (lines 1820–2186); the cache hooks `vllm_omni/diffusion/cache/teacache/hook.py:155` and `magcache/hook.py:182` clone `hidden_states` per step. Separately, `copy.deepcopy(self.scheduler)` / `copy.deepcopy(req.sampling_params)` is copy-pasted across diffusion pipelines — `pipeline_qwen_image.py:786`, `pipeline_hunyuan_image3.py:1904`, `pipeline_ltx2*.py` (×3), `pipeline_dreamzero.py:1085`, `diffusion_model_runner.py:398` — a full object-graph deepcopy on the request path. (Contrast `dreamzero/causal_wan_model.py:203`, which carries a `# No .clone() needed.` comment — the aware pattern.)
-
-### Why dangerous
-A `.clone()` of a GPU tensor or a `copy.deepcopy` of a config object inside a per-step / per-request path is a hidden allocator: it reads as one Python line but triggers a GPU memcpy or a deep object-graph walk every iteration. Across 50 diffusion steps or hundreds of AR steps it dominates latency and VRAM bandwidth. `deepcopy` additionally ignores any custom device / `__copy__` logic and can drag tensors through CPU.
-
-### Severity
-- ⚠ any *new* `.clone()` / `.copy_()` / `copy.deepcopy(...)` inside a per-step loop or per-request path.
-- ✗ for `.clone()` of a full latent/activations tensor inside an AR or diffusion step loop without an explanatory comment, or `copy.deepcopy` of a scheduler / sampling-config on the request hot path.
-
-### Detect (diff-scoped)
-```bash
-git diff ${BASE}...HEAD -- "*.py" | grep "^+[^+]" \
-  | grep -E '\.clone\(\)|\.copy_\(|copy\.deepcopy|deepcopy\('
-```
-
-### Fix
-Tensors: prefer a view (`x[..., :k]`, `torch.narrow`, `as_strided`) or write into a pre-allocated buffer with `dst.copy_(src)` instead of `.clone()`; if the caller no longer needs the original, `move`/`del` it rather than copy. Schedulers / configs: build a fresh lightweight instance per request, or split out the mutable per-request bits so the shared immutable part isn't deepcopied. If a copy is genuinely required (e.g. the source is mutated in place later), keep it and add a one-line comment saying why.
-
----
-
-## 5. Blocking the asyncio event loop / lock held across `await`
-
-### Anti-pattern
-```python
-# BLOCKER-prone: blocking sleep / blocking HTTP / lock held across an await,
-# all inside an async (event-loop) function
-async def handle(self, req):
-    with self._lock:
-        resp = await self._client.call(req)   # lock held across await -> serializes all requests
-    time.sleep(0.1)                           # stalls the single loop for every concurrent request
-```
-
-### Why dangerous
-vLLM-Omni serves over a single asyncio event loop. Any synchronous blocking work on an `async def` path — `time.sleep`, blocking HTTP (`requests`/`urllib`), heavy CPU work, or a lock held across an `await` — stalls the loop for *every* concurrent request, not just the blocking one. A lock held across `await` silently serializes the whole pipeline; blocking I/O tanks throughput and inflates tail latency.
-
-### Severity
-- ⚠ any *new* `time.sleep(`, blocking HTTP call (`requests.get/post`, `urllib.request`, `urlopen`), or `await` inside a `with Lock` / `async with` critical section, in `async def` code.
-- ✗ for `time.sleep` or blocking HTTP on the serving path (`engine/`, `entrypoints/`, async `connectors/`), or a lock acquired and held across an `await` on the request path.
-
-### Detect (diff-scoped)
-```bash
-# New blocking primitives introduced by the diff — then eyeball whether each
-# sits in an async function on the loop vs a dedicated worker thread:
-git diff ${BASE}...HEAD -- "*.py" | grep "^+[^+]" \
-  | grep -E 'time\.sleep|requests\.(get|post|put|delete)|urllib\.request|urlopen'
-# Lock acquired with an await potentially inside the critical section (manual eyeball):
-git diff ${BASE}...HEAD -- "*.py" | grep "^+[^+]" | grep -E 'async with|\.acquire\(\)'
-```
-Note: blocking inside a **dedicated worker thread is correct** — the repo already does this (`diffusion/model_loader/hub_prefetch.py`, `distributed/omni_connectors/kv_transfer_manager.py`, the `mooncake`/`mori` connectors poll with `time.sleep` on their own threads). The check targets the *event-loop* path only.
-
-### Fix
-Move blocking work off the loop with `asyncio.to_thread(...)` / `run_in_executor`, or use a native async client (`httpx.AsyncClient` / `aiohttp`). Never `await` while holding a lock — drop the lock before the `await` and re-acquire after, or restructure so the critical section contains no `await`.
-
----
-
-## Running the sweep
-
-Run all five detections against `${BASE}...HEAD`, then for each hit decide ⚠ vs ✗ using the severity rules above. Roll the results into the report as a single **Code quality** dimension row (count of ⚠ and ✗), alongside the type-specific checklist from [checklists.md](checklists.md).

.claude/skills/precheck-pr/references/examples-policy.md

@@ -1,68 +0,0 @@
-# Examples Python Policy
-
-Prevent new model-specific Python examples without forcing cleanup of the
-existing backlog. Run this check on every PR in quick and full modes.
-
-## Scope
-
-Set the merge base as in the main workflow, then list Python paths introduced
-by the PR, including additions, copies, and renames:
-
-```bash
-BASE="$(git merge-base HEAD origin/main)"
-git diff --name-status --diff-filter=ACR --find-renames --find-copies \
-  "${BASE}"...HEAD -- 'examples/**/*.py'
-```
-
-Inspect destination paths for copies and renames. Existing model-specific files
-that are only modified or deleted are grandfathered and must not be reported.
-
-## Blocking classification
-
-Mark ✗ when a newly introduced Python file does any of the following:
-
-- Names or scopes a path to one model, checkpoint, vendor, or model family.
-- Hard-codes a model identifier, model-specific prompt, request shape, output
-  conversion, or launch configuration behind an otherwise generic filename.
-- Duplicates an existing task/protocol runner to demonstrate one model.
-- Adds a per-model helper below a generic task hub such as `text_to_speech/`.
-
-Do not infer safety from a generic filename alone. For example, a file named
-`text_to_audio.py` is still model-specific if it only implements one model's
-contract.
-
-## Acceptable additions
-
-A new Python example may pass when it is a genuinely model-neutral,
-user-facing task or protocol entrypoint. It must accept model selection through
-configuration and keep model-specific behavior out of the script.
-
-Use ⚠ when the file is model-neutral but reusable logic appears misplaced under
-`examples/`. Route code by purpose:
-
-| Code purpose | Preferred location |
-|---|---|
-| Model prompt, defaults, request/output adaptation | `vllm_omni/model_extras/` or production model modules |
-| Runnable model command and validation evidence | Task documentation or `recipes/` |
-| UI or interactive application | `apps/` |
-| Benchmark or evaluator | `benchmarks/` |
-| Regression reproducer | `tests/` |
-| Download, conversion, or setup utility | `tools/` |
-
-If a model cannot use an existing shared runner, report the missing generic
-capability. Do not solve the gap by adding a model-specific Python example.
-
-## Report format
-
-Add one row to the pre-check report:
-
-```text
-Examples policy    ✓ no new Python example paths
-Examples policy    ⚠ generic helper belongs in tools/
-Examples policy    ✗ examples/offline_inference/new_model/end2end.py is model-specific
-Examples policy    ✗ examples/offline_inference/x_to_y_model_name.py is model-specific
-```
-
-For a blocker, name the path, the model-specific behavior, and the appropriate
-shared runner or destination. Do not propose deleting unrelated existing
-examples as part of the PR.

.claude/skills/quantization/SKILL.md

@@ -1,103 +0,0 @@
----
-name: quantization
-description: Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models. Use when choosing or adding methods such as fp8, int8, gguf, mxfp8, mxfp4, mxfp4_dualscale, ModelOpt, AutoRound, INC, msModelSlim, awq, or gptq; debugging quantized loading; or validating memory, speed, and output quality.
----
-
-# vLLM-Omni Quantization
-
-Use this skill for quantization work in `vllm-omni`. Start from the local
-code and docs, then pick the smallest validated path for the model, method,
-hardware, and quality target.
-
-## First Checks
-
-Before changing code or recommending a command, identify:
-
-- Model and task: AR text, omni/TTS, text-to-image, text-to-video, or multi-stage diffusion.
-- Hardware backend: CUDA generation, Ascend NPU, Intel XPU, or another platform.
-- Quantization mode: online from BF16/FP16 weights, pre-quantized checkpoint, runtime KV/FA quantization, or per-component routing.
-- Scope: transformer/DiT, thinker language model, text encoder, VAE, audio/vision encoder, talker, or a specific stage.
-- Validation target: memory reduction, latency/throughput, output quality, or all three.
-
-Do not assume a method is supported just because the CLI accepts the string.
-Check `docs/user_guide/quantization/` and the closest implementation first.
-
-## Quick Decision
-
-| Task | Start With |
-|------|------------|
-| Choose a method or command | `references/methods.md` and `references/modality-compat.md` |
-| Use `build_quant_config()` or per-component routing | `references/methods.md` |
-| Work on diffusion quantization | `references/diffusion.md` |
-| Add quantization to a new model | `references/adding-models.md` |
-| Convert or load ModelOpt FP8 checkpoints | `references/modelopt-fp8.md` |
-| Debug ModelOpt, GGUF, AutoRound, MXFP, or serialized Int8 loading | `references/diffusion.md` and method docs under `docs/user_guide/quantization/` |
-
-## Current Runtime Shape
-
-The unified entrypoint is:
-
-```python
-from vllm_omni.quantization import build_quant_config
-```
-
-It supports method strings, flat method dictionaries, per-component
-dictionaries, existing `QuantizationConfig` objects, and `None`. The factory
-delegates generic methods to upstream `vllm` and keeps vLLM-Omni overrides for
-diffusion or omni-specific routing:
-
-- `gguf`
-- `int8`
-- `mxfp8`
-- `mxfp4`
-- `mxfp4_dualscale`
-- `inc`, `auto-round`, `auto_round`
-- ModelOpt auto-detected configs: `modelopt`, `modelopt_fp4`, `modelopt_mixed`
-
-Use `ComponentQuantizationConfig` when only one stage or component should be
-quantized. Pre-quantized ModelOpt-style checkpoints should not spill into
-vision/audio encoders that have no corresponding scale tensors.
-
-## Ownership Boundary
-
-- Upstream `vllm` owns generic quantization configs, kernels, loader semantics,
-  hardware capability rules, and generic AR quantization methods.
-- `vllm-omni` owns unified config routing, diffusion-specific wrappers,
-  component scoping, GGUF or ModelOpt checkpoint adapters, model-specific
-  prefix mapping, docs, examples, and validation.
-
-If a new method needs missing generic kernels or loader behavior, fix upstream
-`vllm` first. In `vllm-omni`, add thin integration and model wiring.
-
-## Working Loop
-
-1. Read the local method doc under `docs/user_guide/quantization/`.
-2. Inspect the active factory and config class in `vllm_omni/quantization/`.
-3. Inspect the target model pipeline and transformer for stable prefixes and
-   whether every relevant vLLM linear layer receives `quant_config`.
-4. For pre-quantized checkpoints, inspect `transformer/config.json` and the
-   checkpoint tensor names before running full generation.
-5. Validate with the same prompt, seed, size, scheduler, steps, dtype, eager or
-   non-eager mode, and parallelism as the BF16 baseline.
-6. Report quality, latency, and memory separately. Do not call a method
-   supported until quality is checked.
-
-## Common Mistakes
-
-| Symptom | Likely Cause | Fix |
-|---------|--------------|-----|
-| `--quantization` has no visible effect | Wrong scope or unsupported model path | Check component routing and method docs |
-| Some layers stay BF16 unexpectedly | `quant_config` was not threaded into all vLLM linear layers | Audit transformer constructors and prefixes |
-| Quality collapses but loading succeeds | Too many sensitive layers were quantized | Add model-specific `ignored_layers` and compare to BF16 |
-| ModelOpt checkpoint loads but output is corrupted | Prefixes, packed-module mapping, scale routing, or BF16 fallback is wrong | Use `references/modelopt-fp8.md` |
-| GGUF shape or tensor mismatch | Missing architecture-specific adapter | Add explicit adapter mapping; avoid generic fallback |
-| Online and offline MXFP4 disagree | Wrong `mxfp4` vs `mxfp4_dualscale` mode | Check `docs/user_guide/quantization/mxfp4.md` |
-| Quantized path is slower than BF16 | Kernel path, compile mode, dtype, or shape mismatch | Compare eager-to-eager and non-eager-to-non-eager |
-
-## References
-
-- General methods and config routing: [references/methods.md](references/methods.md)
-- Modality and model scope: [references/modality-compat.md](references/modality-compat.md)
-- Diffusion implementation patterns: [references/diffusion.md](references/diffusion.md)
-- Adding model support: [references/adding-models.md](references/adding-models.md)
-- ModelOpt FP8 conversion and loading: [references/modelopt-fp8.md](references/modelopt-fp8.md)

.claude/skills/quantization/references/adding-models.md

@@ -1,70 +0,0 @@
-# Adding Quantization Support to a Model
-
-Use this checklist when extending quantization to a new architecture or stage.
-
-## Classify Ownership
-
-| Case | Owner |
-|------|-------|
-| New generic AR method, kernel, or loader semantics | upstream `vllm` first |
-| Existing upstream method needs diffusion wiring | `vllm-omni` model and config integration |
-| GGUF or ModelOpt tensor mapping for a diffusion architecture | `vllm-omni` adapter |
-| NPU MXFP or msModelSlim diffusion path | `vllm-omni` platform/method wrapper and docs |
-| Multi-stage omni checkpoint quantizes only the thinker LM | `vllm-omni` component scoping |
-
-Avoid building a private quantization stack in model code.
-
-## Model Wiring Checklist
-
-1. Find the closest supported model implementation.
-2. Confirm the model uses vLLM linear layers that accept `quant_config`.
-3. Add `quant_config` to the transformer constructor.
-4. Pass stable `prefix` values through every linear layer.
-5. Handle fused modules and packed mappings explicitly.
-6. Ensure `load_weights()` and any `WeightsMapper` remap `ignored_layers` or
-   `modules_to_not_convert`.
-7. Keep tokenizer, scheduler, VAE, text encoder, audio/vision encoders, and
-   talker BF16 unless method-specific docs validate them.
-8. Add or update a method doc under `docs/user_guide/quantization/`.
-
-## Checkpoint Adapter Checklist
-
-For pre-quantized checkpoints:
-
-- Inspect `transformer/config.json` first.
-- Check `quant_method`, `method`, `producer.name`, `quant_algo`, serialized
-  flags, `ignored_layers`, and any method-specific fields.
-- Verify tensor name mapping before generation.
-- Verify packed modules such as `to_qkv`, `add_kv_proj`, and `w13`.
-- Confirm scale tensor names and shapes.
-- Allow dequantization back to BF16 for intentionally skipped target layers.
-
-## Sensitive Layer Discovery
-
-Start conservative. Quantize the backbone first and keep output-side or routing
-layers BF16 until quality is proven.
-
-Frequently sensitive areas:
-
-- attention output projections such as `to_out`
-- FFN down projections such as `w2`
-- final projections such as `proj_out`, `final_layer`, and output heads
-- modulation, timestep, position, image, or text embedders
-- refiner blocks
-- MoE routers, experts selected by routing, and layernorm-adjacent modules
-- VAE, text/vision towers, audio encoders, and codec/talker stages
-
-Do not reuse one model family's ignore list blindly.
-
-## Tests and Evidence
-
-Minimum evidence for a PR:
-
-- loader/config test or smoke command
-- fixed-seed BF16 vs quantized output comparison
-- quality metrics and saved outputs for precision-changing work
-- memory and latency comparison under identical execution mode
-- failure behavior for unsupported models or missing checkpoint fields
-
-When the PR adds a method to a support table, include the exact model,
-hardware, command, quality threshold, and artifact path used for validation.

.claude/skills/quantization/references/diffusion.md

@@ -1,113 +0,0 @@
-# Diffusion Quantization Reference
-
-Use this file for DiT quantization, config routing, checkpoint adapters, and
-quality or loader debugging.
-
-## Supported Method Families
-
-The current local diffusion quantization families are:
-
-- CUDA/GPU online or checkpoint: `fp8`, `int8`, `gguf`, ModelOpt
-- Ascend NPU: `int8`, `mxfp8`, `mxfp4`, `mxfp4_dualscale`, msModelSlim paths
-- Intel XPU: AutoRound/INC and online MXFP8 paths where documented
-
-Always cross-check the method doc before claiming model support. The CLI
-accepting a method string is not enough.
-
-## Implementation Starting Points
-
-| Area | Files |
-|------|-------|
-| Unified factory | `vllm_omni/quantization/factory.py` |
-| Per-component routing | `vllm_omni/quantization/component_config.py` |
-| GGUF diffusion method | `vllm_omni/quantization/gguf_config.py` |
-| Int8 diffusion method | `vllm_omni/quantization/int8_config.py` |
-| MXFP8 diffusion method | `vllm_omni/quantization/mxfp8_config.py` |
-| MXFP4 and dual-scale method | `vllm_omni/quantization/mxfp4_config.py` |
-| AutoRound/INC omni extension | `vllm_omni/quantization/inc_config.py` |
-| ModelOpt checkpoint adapters | `vllm_omni/diffusion/model_loader/checkpoint_adapters/modelopt.py` |
-| FP8 scaled-mm runtime patches | `vllm_omni/patch.py` |
-| Similarity tool | `vllm_omni/quantization/tools/compare_diffusion_trajectory_similarity.py` |
-
-## Threading `quant_config`
-
-For a diffusion transformer:
-
-1. Accept `quant_config: QuantizationConfig | None` in the transformer.
-2. Pass `quant_config` and stable `prefix` values to every vLLM linear layer.
-3. Preserve packed-module mappings for fused QKV, FFN, or model-specific fused
-   projections.
-4. Call `apply_vllm_mapper()` on configs that need HF-to-vLLM name remapping.
-5. For component configs, keep prefixes specific enough to avoid quantizing VAE
-   or encoders by accident.
-
-Common skipped areas are `proj_out`, output projections, modulation layers,
-embedders, refiner blocks, MoE routers, and layernorm-adjacent paths.
-
-## Online vs Offline
-
-Online quantization:
-
-- starts from BF16/FP16 checkpoint weights
-- computes or stores quantized weights at load time
-- typically uses `--quantization <method>` or `quantization="<method>"`
-
-Offline or pre-quantized checkpoints:
-
-- include quantized weights and scales on disk
-- usually carry `quantization_config` in `transformer/config.json`
-- should auto-detect when the config is complete
-- may require model-specific adapter logic for tensor names and packed modules
-
-Do not mix online flags with incompatible offline checkpoint configs. If the
-active config and disk config differ, `resolve_quant_config_from_disk()` should
-raise or rebuild rather than silently loading corrupted weights.
-
-## GGUF Rules
-
-- Require `quantization_config.gguf_model`.
-- Use the normal base model for tokenizer, scheduler, text encoder, and VAE.
-- Add explicit architecture adapters for tensor-name mapping.
-- Use `named_parameters()` and `named_buffers()`, not `state_dict()`, to
-  discover loadable names.
-- Guard fused QKV/KV rewrites so tensors are not rewritten twice.
-- Flatten N-D activations around the GGUF matmul and restore shape.
-
-Unsupported architectures should fail clearly instead of falling back to a fake
-generic mapper.
-
-## MXFP Rules
-
-- `mxfp8` is W8A8 microscaling, currently centered on NPU and documented XPU
-  behavior.
-- `mxfp4` is online single-scale W4A4 on NPU.
-- `mxfp4_dualscale` is online/offline dual-scale W4A4 with BF16 fallback; the
-  offline path is the production path when calibrated `mul_scale` exists.
-- Offline dual-scale checkpoints must inject per-transformer `ignored_layers`
-  into config because cascade transformers can have different BF16 fallback
-  sets.
-
-Do not load an offline dual-scale checkpoint with the online single-scale path.
-
-## Common Failures
-
-| Symptom | Likely Cause | Fix |
-|---------|--------------|-----|
-| `Unknown quantization method` | Factory override or upstream registration is missing | Add the right override or upstream method |
-| Missing scale tensors | Wrong scope, wrong adapter, or BF16 layer not allowed to dequantize | Check config scope and adapter scale routing |
-| Output rank collapses from 3-D to 2-D | FP8 scaled-mm kernel ignored output shape | Check the patch in `vllm_omni/patch.py` |
-| Quality degrades silently | Sensitive layers quantized | Add `ignored_layers`; compare to BF16 |
-| Only one cascade transformer works | Disk config differs per transformer but active config is reused | Rebuild from each transformer's config |
-| Quantized path slower than BF16 | Kernel, dtype, compile, or benchmark mode mismatch | Compare eager-to-eager and non-eager-to-non-eager |
-
-## Verification
-
-For a new or changed diffusion quantization path, run:
-
-1. Config and loader smoke test.
-2. One fixed-seed generation against BF16.
-3. Numeric comparison with the similarity tool or equivalent metrics.
-4. Serving test if the path is user-facing online.
-5. Memory and latency check under the same execution mode as the baseline.
-
-Keep output artifacts when precision changes are part of the PR.

.claude/skills/quantization/references/methods.md

@@ -1,82 +0,0 @@
-# General Quantization Methods
-
-Use this file for method selection and unified `vllm-omni` config syntax. For
-diffusion-specific wiring, see `diffusion.md`. For ModelOpt checkpoint export
-and loading details, see `modelopt-fp8.md`.
-
-## Unified Entry Point
-
-`vllm_omni.quantization.build_quant_config()` accepts:
-
-- `None` or `"none"` to disable quantization
-- a method string such as `"fp8"`, `"int8"`, `"mxfp8"`, `"awq"`, or `"auto-round"`
-- a flat dict with `"method"` or `"quant_method"`
-- a per-component dict such as `{"transformer": {"method": "fp8"}, "vae": None}`
-- an already-built `QuantizationConfig`
-
-Per-component dicts are routed by `ComponentQuantizationConfig` using
-longest-prefix matching. Prefix stability matters: if a model remaps HF names
-to vLLM names, apply the mapper to `ignored_layers` or component prefixes.
-
-## Local Overrides
-
-The local factory delegates most methods to upstream `vllm`, but has vLLM-Omni
-overrides for methods that need diffusion, NPU, XPU, or component behavior:
-
-| Method | Local Config | Main Use |
-|--------|--------------|----------|
-| `gguf` | `DiffusionGGUFConfig` | Pre-quantized diffusion transformer weights |
-| `int8` | `DiffusionInt8Config` | Online or serialized W8A8 diffusion transformers |
-| `mxfp8` | `DiffusionMXFP8Config` | W8A8 MXFP8 diffusion on NPU and online XPU path |
-| `mxfp4` | `DiffusionMXFP4Config` | Online W4A4 MXFP4 diffusion on NPU |
-| `mxfp4_dualscale` | `DiffusionMXFP4DualScaleMixedConfig` | Online/offline W4A4 dual-scale plus BF16 fallback on NPU |
-| `inc`, `auto-round`, `auto_round` | `OmniINCConfig` | AutoRound/INC checkpoint loading, including MXFP8 checkpoint metadata |
-| ModelOpt config dicts | upstream ModelOpt configs through auto-detect | FP8, NVFP4, or mixed ModelOpt checkpoints |
-
-Check `SUPPORTED_QUANTIZATION_METHODS` in `vllm_omni/quantization/factory.py`
-before adding a new method name.
-
-## AR and Generic Quantization
-
-For AR-backed models, upstream `vllm` methods usually apply:
-
-- `awq` and `gptq`: 4-bit or 8-bit weight quantization with calibration,
-  commonly used for text and AR stages.
-- `fp8`: FP8 weight path or KV-cache FP8 depending on flags and hardware.
-- `inc` or `auto-round`: pre-quantized checkpoints with Intel Neural
-  Compressor / AutoRound metadata.
-
-Use these for the AR language model stage only when the checkpoint and model
-guide support it. Omni and TTS models often keep audio, vision, talker, and
-codec stages in BF16.
-
-## Diffusion and Offline Methods
-
-For diffusion transformers, prefer the method-specific docs:
-
-- `docs/user_guide/quantization/fp8.md`
-- `docs/user_guide/quantization/int8.md`
-- `docs/user_guide/quantization/gguf.md`
-- `docs/user_guide/quantization/modelopt.md`
-- `docs/user_guide/quantization/mxfp8.md`
-- `docs/user_guide/quantization/mxfp4.md`
-- `docs/user_guide/quantization/autoround.md`
-- `docs/user_guide/quantization/msmodelslim.md`
-
-Pre-quantized checkpoints should normally auto-detect from config. Runtime
-flags such as `--force-cutlass-fp8`, `--linear-backend cutlass`, and
-`--moe-backend cutlass` select kernels; they do not quantize a BF16 checkpoint.
-
-## Validation
-
-Use fixed-seed A/B comparisons and record:
-
-- model path and quantized checkpoint path
-- method config and `ignored_layers`
-- prompt, size, frame count, steps, scheduler, dtype, and seed
-- eager/non-eager mode, compile flags, and parallelism
-- output metrics such as PSNR, MAE, cosine similarity, SSIM, LPIPS, plus visual artifacts
-- latency and peak memory, reported separately from quality
-
-The helper `vllm_omni.quantization.tools.compare_diffusion_trajectory_similarity`
-is the default lightweight image/video comparison tool for diffusion paths.

.claude/skills/quantization/references/modality-compat.md

@@ -1,47 +0,0 @@
-# Quantization Compatibility by Modality
-
-Use this as a routing guide. The source of truth is the local method docs under
-`docs/user_guide/quantization/` and the current model implementation.
-
-## Summary
-
-- AR and omni language-model quantization mostly follows upstream `vllm`, with
-  vLLM-Omni scoping for multi-stage models.
-- Diffusion quantization is method-specific and model-specific. It usually
-  targets the diffusion transformer only.
-- Pre-quantized checkpoints should quantize only the component that has
-  quantized weights and scale tensors.
-
-## Model Type Matrix
-
-| Model Type | Typical Quantization Scope | Notes |
-|------------|----------------------------|-------|
-| AR text models | Language model | Upstream `vllm` methods usually apply |
-| Omni/TTS models | Thinker or AR language-model stage | Audio, vision, talker, and codec stages usually stay BF16 |
-| DiT image models | Diffusion transformer | Check FP8, Int8, GGUF, ModelOpt, AutoRound docs |
-| DiT video models | Diffusion transformer | HunyuanVideo FP8 and Wan2.2 MXFP paths are documented; validate other video paths |
-| Multi-stage diffusion | Selected stage only | Use per-component routing and per-stage validation |
-| Audio diffusion | Usually unsupported | Prefer dtype, offload, cache, or parallelism unless docs say otherwise |
-
-## Method Hints
-
-| Goal | Candidate |
-|------|-----------|
-| AR memory reduction | AWQ, GPTQ, AutoRound, ModelOpt where checkpoint supports it |
-| CUDA diffusion W8A8 | FP8 or Int8 |
-| Pre-quantized CUDA diffusion checkpoint | ModelOpt or GGUF |
-| Ascend NPU diffusion | Int8, MXFP8, MXFP4, MXFP4 DualScale, msModelSlim |
-| Intel XPU checkpoint | AutoRound/INC paths |
-| Conservative image quality | selective FP8/Int8 with `ignored_layers` |
-| Unsupported diffusion model | cache acceleration, CPU/layerwise offload, dtype, TP/SP/CFG parallelism |
-
-## Validation Rule
-
-Compatibility means more than successful loading. A method is compatible only
-after it has:
-
-- correct component scope
-- complete checkpoint/config metadata if offline
-- fixed-seed quality comparison against BF16
-- acceptable latency and memory behavior
-- docs or examples that state model, method, hardware, and caveats

.claude/skills/quantization/references/modelopt-fp8.md

@@ -1,122 +0,0 @@
-# ModelOpt FP8 Conversion and Loading
-
-Use this when exporting or loading ModelOpt FP8 checkpoints for diffusion
-transformers. This reference captures the practical conversion lessons from the
-2026-04-21 ModelOpt FP8 paste and aligns them with the current
-`vllm-omni` ModelOpt adapter.
-
-## Core Rule
-
-Treat ModelOpt FP8 as selective checkpoint quantization, not one-click
-whole-model FP8. Quantize the main transformer or DiT backbone, keep sensitive
-or peripheral modules BF16, serialize a complete ModelOpt checkpoint, and let
-vLLM-Omni auto-detect it from config.
-
-Do not pass `--quantization fp8` to force a ModelOpt checkpoint path. The
-checkpoint's `quantization_config` should select `modelopt`.
-
-## Conversion Strategy
-
-Prefer:
-
-- backbone attention Q/K/V and FFN expansion projections
-- conservative per-model ignore lists
-- MHA quantizers disabled until basic linear quantization is stable
-- full module-name prefixes in ignore/routing logic
-- BF16 fallback for output-side and routing-sensitive layers
-
-Avoid quantizing by default:
-
-- VAE
-- text, vision, or audio encoders
-- embedders and modulation layers
-- final heads and output projections
-- refiner modules
-- MoE routers and layernorm-sensitive blocks
-
-## Model-Specific Starting Points
-
-| Model Family | Quantize First | Keep BF16 First |
-|--------------|----------------|-----------------|
-| Z-Image | attention q/k/v, FFN w1/w3 | `to_out`, `w2`, `noise_refiner`, `context_refiner`, embedders, modulation, final/output |
-| Qwen-Image | transformer backbone linear layers | `proj_out`, `img_in`, `txt_in`, norms, modulation, position/time/embed layers |
-| FLUX2-dev / FLUX2-klein | backbone linear layers | `proj_out`, context/x embedders, `norm_out`, stream modulation, time embeddings |
-| HunyuanImage-3.0 | `model.model` backbone | VAE, vision tower, token/time/image embedders, final image head, LM head, routers, layernorm-sensitive blocks |
-
-These are starting points, not support claims. Validate with BF16 outputs.
-
-## Required Checkpoint Metadata
-
-`transformer/config.json` must include a complete `quantization_config`.
-At minimum it should identify ModelOpt and the algorithm:
-
-```json
-{
-  "quantization_config": {
-    "producer": {"name": "modelopt"},
-    "quant_method": "modelopt",
-    "quant_algo": "FP8"
-  }
-}
-```
-
-Current vLLM-Omni auto-detects:
-
-- `FP8` and `FP8_PER_CHANNEL_PER_TOKEN` -> `modelopt`
-- `NVFP4` -> `modelopt_fp4`
-- `MIXED_PRECISION` -> `modelopt_mixed`
-
-Packed modules and scales must map correctly:
-
-- `to_qkv` from `to_q`, `to_k`, `to_v`
-- `add_kv_proj` from `add_q_proj`, `add_k_proj`, `add_v_proj`
-- `w13` from `w1`, `w3`
-- `.input_scale`, `.weight_scale`, `.weight_scale_2`, `.weight_scale_inv`
-
-For selective FP8, target layers that remain BF16 must be allowed to
-dequantize from FP8 weights using the matching `weight_scale`, or the adapter
-must skip the quantized scale tensors for that BF16 target.
-
-## Runtime Signals
-
-Healthy loading should show ModelOpt auto-detection and a ModelOpt linear
-kernel path. Useful signals include:
-
-- auto-detected quantization from config
-- selected ModelOpt FP8 linear method
-- CUTLASS or FlashInfer FP8 scaled-mm backend when enabled and supported
-- non-eager path compiling the transformer when expected
-
-If online serving fails while offline inference works, inspect warmup and
-serving initialization before changing checkpoint conversion.
-
-## Validation Order
-
-1. Check config completeness.
-2. Run an export checker such as `examples/quantization/check_modelopt_fp8_export.py`.
-3. Confirm actual FP8 tensors and expected disk-size reduction.
-4. Run one offline generation with fixed prompt, seed, size, and steps.
-5. Run serving with `vllm serve --omni` and verify `/v1/images/generations`.
-6. Compare against BF16 using visual review plus metrics such as LPIPS, PSNR,
-   MAE, cosine similarity, and SSIM.
-7. Compare performance only under matched modes:
-   - BF16 eager vs FP8 eager
-   - BF16 non-eager vs FP8 non-eager
-
-FP8 is not automatically faster. Check whether execution reaches FP8 kernels,
-whether compile mode is comparable, and whether the workload shape fits the
-kernel path.
-
-## Triage
-
-| Symptom | First Check |
-|---------|-------------|
-| Startup failure | `config.json`, `model_index.json`, `quantization_config`, missing scales |
-| Loads but output is corrupted | Over-quantized sensitive layers or wrong full-name prefixes |
-| Offline works but online fails | Dummy warmup, serving init, compile path |
-| FP8 is not faster | Kernel selection, dtype, compile mode, workload shape |
-| BF16 fallback fails | Missing `weight_scale` for dequantization or wrong packed-module mapping |
-
-The success criterion is stable, correctly scoped checkpoint loading with
-quality preserved enough for the target use case, not maximizing the number of
-FP8 layers.

.claude/skills/readme.md

@@ -1,9 +1,9 @@
-# Repository Skills for vLLM-Omni
+# Claude Skills for vLLM-Omni
 
-This directory contains repository-scale skills maintained for `vllm-omni`.
+This directory contains Claude Code skills maintained for the `vllm-omni`
-They capture repeatable workflows for common contributor and maintainer tasks
+repository. These skills capture repeatable workflows for common contributor
-such as model integration, CI-aligned testing, performance optimization, and
+tasks such as model integration, pull request review, and release note
-pull request review.
+generation.
 
 ## Directory Structure
 
@@ -14,41 +14,18 @@ include:
 - `references/`: focused reference material used by the skill
 - `scripts/`: small helper scripts used by the skill
 
-## Using the Skills
-
-Coding agents that discover repository skills can invoke the relevant skill by
-name. For other agents, point them to the skill's `SKILL.md` and ask them to
-read it before changing code. Combine a domain skill with `vllm-omni-test` when
-tests or CI coverage change, then use `precheck-pr` for the contributor's final
-self-check.
-
 ## Available Skills
 
-- [`add-diffusion-model`](add-diffusion-model/SKILL.md): guides integration of
+- `add-diffusion-model`: guides integration of a new diffusion model into
-  a new diffusion model into `vllm-omni`
+  `vllm-omni`
-- [`add-tts-model`](add-tts-model/SKILL.md): covers integration of new TTS
+- `diffusion-perf-opt`: guides diffusion model performance optimization,
-  models and related serving workflows
+  including profiling traces, parallel strategies, stage timing analysis, and
-- [`diffusion-perf-opt`](diffusion-perf-opt/SKILL.md): guides diffusion model
+  benchmark-driven tuning
-  performance optimization, including profiling traces, parallel strategies,
+- `add-omni-model`: covers addition of new omni-modality model support
-  stage timing analysis, and benchmark-driven tuning
+- `add-tts-model`: covers integration of new TTS models and related serving
-- [`precheck-pr`](precheck-pr/SKILL.md): self-checks a branch before creating a
+  workflows
-  PR by validating title format, dead code, accuracy and performance claims,
+- `generate-release-note`: helps prepare release notes for repository changes
-  and merge readiness
+- `review-pr`: provides a structured workflow for reviewing pull requests
-- [`quantization`](quantization/SKILL.md): guides quantization method selection,
-  model integration, checkpoint loading, and quality/performance validation
-  for vLLM-Omni
-- [`review-pr`](review-pr/SKILL.md): provides a frozen-snapshot, contract-aware
-  workflow for maintainers and reviewers; contributors should use
-  `precheck-pr` for self-review
-- [`vllm-omni-npu-model-runner-upgrade`](vllm-omni-npu-upgrade/SKILL.md):
-  upgrades NPU model runners to align with the latest vllm-ascend
-  `NPUModelRunner`
-- [`vllm-omni-test`](vllm-omni-test/SKILL.md): guides generation and execution
-  of CI-aligned tests (L1–L4), pytest marker selection (`core_model` /
-  `advanced_model` / `full_model`, `omni` / `tts` / `diffusion`), Buildkite
-  wiring (`test-ready.yml`, `test-merge.yml`, `test-nightly.yml`,
-  `test-weekly.yml`), and copy-paste local plus CI-like `pytest` commands; see
-  `references/test-routing.md` for level-to-command mapping
 
 ## Maintenance Guidelines
 

.claude/skills/review-pr/SKILL.md

@@ -1,239 +0,0 @@
----
-name: review-pr
-description: Review pull requests and local branches for vllm-project/vllm-omni with a frozen snapshot, module-design ownership, feature-design overlays, targeted validation, and concise evidence-backed findings. Use for default, detailed, or repeat maintainer reviews; checking correctness, compatibility, tests, benchmarks, model additions, distributed changes, or breaking behavior; and identifying or explicitly requesting the most relevant code-owner reviewers. Use precheck-pr instead for an author's pre-submit self-check.
----
-
-# Review vLLM-Omni Pull Requests
-
-Review like a maintainer: direct, selective, and focused on issues that CI does
-not prove. Prefer a few high-confidence findings over exhaustive commentary.
-Zero findings is a valid result.
-
-## Quality contract
-
-Make every finding:
-
-- **Correct:** prove a reachable failure, not a suspicion.
-- **Prioritized:** lead with merge blockers and high-impact defects.
-- **Actionable:** identify the smallest safe fix direction.
-- **Evidence-based:** cite code, tests, docs, CI, or measurements.
-- **Concise:** avoid review templates and repeated summaries.
-- **Calibrated:** match severity to user and maintainer impact.
-
-Do not report unrelated backlog, style already enforced by pre-commit, or a
-missing test that would not protect changed behavior.
-
-## Select the input and depth
-
-Use `vllm-project/vllm-omni` as the base repository. Accept its forks and local
-checkouts; use another skill for unrelated repositories.
-
-| Input | Review surface |
-| --- | --- |
-| PR number or URL | Frozen PR metadata, full diff, and relevant threads. |
-| Local branch/worktree | Frozen target-base SHA through committed, staged, unstaged, and in-scope untracked changes. |
-| Pre-filled context | Reuse supplied metadata; fetch only missing facts and the full diff. |
-
-Default to maintainer brevity. A detailed or audit request expands coverage and
-lists `path:line` findings, but keeps the same confidence and severity bar.
-
-## Reference guide
-
-Load references in review order: process, one primary module contract, matching
-feature designs, evidence checks, then delivery. Every file is linked directly
-below; do not load unrelated module references.
-
-Each concise reference links to the maintained
-[vLLM-Omni documentation](https://docs.vllm.ai/projects/vllm-omni/en/latest/).
-For branch-specific behavior, inspect the matching `docs/` file in the reviewed
-checkout first; use the published latest docs for current guidance and discovery.
-If docs and live code disagree, verify the code/tests and report the drift.
-
-### Review process
-
-| Reference | Read when |
-| --- | --- |
-| [review-execution.md](references/process/review-execution.md) | Every review; freeze inputs, inspect safely, and deliver against the same snapshot. |
-| [general-checks.md](references/process/general-checks.md) | Every review; apply repository-wide correctness and evidence rules. |
-| [design-contracts.md](references/process/design-contracts.md) | Every production review; resolve branch-local module and feature design status. |
-| [review-routing.md](references/process/review-routing.md) | After the diff census; select one primary module and conditional overlays. |
-
-### Primary module contract
-
-| Reference | Read when |
-| --- | --- |
-| [entrypoints.md](references/modules/entrypoints.md) | Offline/CLI/API ingress, validation, rendering, streaming, or sessions change. |
-| [configuration.md](references/modules/configuration.md) | Config construction, deploy/stage schema, defaults, registry, or topology changes. |
-| [input-output-modality.md](references/modules/input-output-modality.md) | Requests, messages, serialization, output types, accumulation, or completion change. |
-| [error-contracts.md](references/modules/error-contracts.md) | Error classification, fatality, propagation, sanitization, or rendering changes. |
-| [engine-orchestration.md](references/modules/engine-orchestration.md) | Cross-stage routing, request state, output ordering, RPC correlation, or terminal convergence changes. |
-| [stage-runtime.md](references/modules/stage-runtime.md) | Placement, startup, readiness, replica identity, affinity, membership, or shutdown changes. |
-| [omni-connector.md](references/modules/omni-connector.md) | Cross-stage/process/device/node transport or synchronization changes. |
-| [model-integration.md](references/modules/model-integration.md) | Registration, preprocessing, loading, runners, or model-specific execution changes. |
-| [ar-runtime.md](references/modules/ar-runtime.md) | AR scheduling, request/cache state, adapters, workers, or upstream vLLM semantics change. |
-| [diffusion.md](references/modules/diffusion.md) | Diffusion runtime, models, batching, parallelism, or offload changes. |
-| [execution-platforms.md](references/modules/execution-platforms.md) | Hardware selection, capabilities, vendor workers, kernels, or patches change. |
-| [cache-management.md](references/modules/cache-management.md) | Cache identity, reuse, validity, reset, eviction, or teardown changes. |
-| [quantization.md](references/modules/quantization.md) | Quantization selection, checkpoint metadata, layer mapping, precision, or constraints change. |
-| [observability.md](references/modules/observability.md) | Metrics, logs, units, labels, correlation, or lifecycle changes. |
-| [profiling.md](references/modules/profiling.md) | Profiling instrumentation, traces, start/stop lifecycle, or overhead changes. |
-| [benchmarking.md](references/modules/benchmarking.md) | Benchmark workload, metric calculation, CLI, or result metadata changes. |
-
-### Feature-design overlays
-
-| Reference | Read when |
-| --- | --- |
-| [runtime-stage-execution.md](references/features/runtime-stage-execution.md) | Disaggregated inference, async chunk/output/materialization, or prefix caching changes. |
-| [communication.md](references/features/communication.md) | A concrete OmniConnector backend or its deployment contract changes. |
-| [diffusion-acceleration.md](references/features/diffusion-acceleration.md) | Diffusion parallelism, attention, quantization, cache, batching, or offload changes. |
-| [infrastructure-performance.md](references/features/infrastructure-performance.md) | Metrics infrastructure or documented speech optimization stacks change. |
-
-### Evidence and quality checks
-
-| Reference | Read when |
-| --- | --- |
-| [model-addition-checklist.md](references/checks/model-addition-checklist.md) | A model, architecture, loader, processor, registry, or stage config is added. |
-| [perf-verification.md](references/checks/perf-verification.md) | The PR makes a latency, throughput, memory, or quality claim. |
-| [test-quality-evaluation.md](references/checks/test-quality-evaluation.md) | Tests change, are absent for risky code, or may not exercise production behavior. |
-| [tests-docs-checklist.md](references/checks/tests-docs-checklist.md) | Coverage, CI markers, examples, user docs, or PR evidence need review. |
-| [verification.md](references/checks/verification.md) | Hardware, a server, or a runnable affected path is available for active verification. |
-| [examples-policy.md](../precheck-pr/references/examples-policy.md) | The PR adds, copies, or renames Python under `examples/`; apply the canonical policy shared with `precheck-pr`. |
-
-### Delivery and reviewer coordination
-
-| Reference | Read when |
-| --- | --- |
-| [maintainer-style-study.md](references/delivery/maintainer-style-study.md) | Findings are ready for concise maintainer-style delivery. |
-| [review-requests.md](references/delivery/review-requests.md) | The user asks to identify, suggest, request, or ping code-owner reviewers. |
-
-## Workflow
-
-### 1. Freeze and report the snapshot
-
-Pin the base and head before reading source or running validation. Within 60 seconds,
-report the pinned head, CI, mergeability, and preliminary findings in the host
-conversation. Do not wait for CI or post this update to GitHub.
-
-If the target changes while fetching, discard the evidence and retry once. If
-it changes again, report the churn and wait for a stable target.
-
-For a trusted PR head, materialize the pinned head in an isolated detached
-worktree. A worktree freezes identity but is not a security sandbox. Treat fork
-heads as untrusted unless the user and environment policy explicitly establish
-otherwise: execute them only in a disposable, secret-free sandbox with restricted
-filesystem, network, and resources; without one, use static SHA-addressed reads
-and CI evidence only. For a local review, freeze the committed, index, worktree,
-and NUL-safe in-scope untracked contents. Follow
-[review-execution.md](references/process/review-execution.md) for trust gates,
-state fingerprints, and byte-for-byte staleness checks.
-
-### 2. Build the diff census
-
-Group files into production code, tests, docs, configuration, build/CI, and
-generated artifacts. Map each changed production file and test group to the PR
-goal. Compare the title/body claims with the actual diff; use linked issues only
-when they define the contract or reproduction.
-
-Mark unrelated scope and unexplained generated artifacts. Do not infer behavior
-from the PR description without tracing the live code.
-
-### 3. Route from the live behavior
-
-Trace each claimed behavior through the changed producer to its live consumer,
-then use [design-contracts.md](references/process/design-contracts.md) and
-[review-routing.md](references/process/review-routing.md) to select one primary
-module contract, a second only for a real documented cross-boundary call path,
-and every matching feature-design and evidence overlay. Treat titles and paths
-as hints; live behavior and the frozen head's current design metadata are
-authoritative. For docs-, tests-, or CI-only changes, route to the production
-contract they protect or use only the applicable evidence checks.
-
-### 4. Run the blocker scan
-
-Apply every category in [general-checks.md](references/process/general-checks.md) before
-lower-priority comments.
-
-If the diff census contains an added, copied, or renamed Python path under
-`examples/`, read and apply the canonical
-[examples policy](../precheck-pr/references/examples-policy.md). Treat a new
-model-specific Python example as blocking. Do not flag model-specific example
-debt that the PR only modifies or removes, and do not run the rest of the
-author-oriented `precheck-pr` workflow.
-
-For each changed value or behavior, trace:
-
-```text
-public ingress -> validation/defaulting -> producer -> transformations
-  -> stage/worker/connector boundary -> final consumer -> terminal cleanup
-```
-
-Cover every applicable offline/online, streaming/non-streaming, sync/async,
-feature-on/off, topology, and compatibility path. Search bounded callers and
-sibling implementations rather than assuming the changed hunk is the only path.
-
-### 5. Apply module and feature contracts
-
-Apply the reference set selected in step 3 and any matching repo-local skill.
-Read the exact module and feature pages in the frozen head, including status,
-ownership boundary, dependencies, candidate invariants, safe-change guide, and
-promotion gate. Candidate or draft rules are questions, not blockers, unless
-current code, tests, or policy enforce them. Inspect both sides of any config,
-registry, serialization, connector, cache, or stage boundary.
-
-When a diff adds or expands a helper, class, fallback, compatibility branch, or
-public behavior, run a subtraction pass: remove out-of-scope behavior and check
-whether each new abstraction can be deleted, merged, moved, or inlined.
-
-### 6. Verify the changed path
-
-Before each validation group, verify the frozen SHA plus the tracked, index,
-untracked, and ignored-file fingerprint, or recreate a pristine snapshot. On a
-trusted head or inside the required sandbox, run an import/version preflight,
-then the narrowest relevant tests and low-cost static checks. Bind every result
-to the head SHA, snapshot fingerprint, and environment fingerprint. Never run
-imports, tests, builds, hooks, or repo-configurable tooling from an untrusted
-head on the reviewer host.
-
-- Treat CI as status evidence; inspect only the first overlapping failure.
-- For docs-only changes, use diff hygiene, links/build checks, and bounded live
-  contract verification instead of dependency setup or pytest.
-- For hardware-dependent paths, run available static/CPU checks and name the
-  exact GPU/NPU gap. Never simulate device evidence.
-- For performance or accuracy claims, require comparable base/head runs with
-  the same environment, workload, warmup, repetitions, and quality criteria.
-
-Stop when each changed semantic path has a supported finding or an explicit
-no-issue conclusion. Do not search further only to increase confidence.
-
-### 7. Consolidate and deliver
-
-Verify each finding against the current diff, deduplicate by root cause, and
-order by severity.
-
-Re-read the remote head and reverify or recreate the pristine validation
-snapshot immediately before delivery. If either changed, mark the review stale
-and restart from the new snapshot.
-
-Return findings first. Use
-[maintainer-style-study.md](references/delivery/maintainer-style-study.md) to keep them
-direct and brief. Each finding must include an exact `path:line`, trigger or
-call path, current behavior, impact, and smallest fix direction. If there are
-no findings, say so briefly and name material validation gaps.
-
-Keep the review read-only unless the user explicitly authorizes posting. Do not
-submit `APPROVE`, `COMMENT`, or `REQUEST_CHANGES`, add labels, edit code, or push
-commits as an implied part of review.
-
-### 8. Optionally request focused owner reviews
-
-Only when the user asks to identify or request reviewers, read
-[review-requests.md](references/delivery/review-requests.md). Rank path-matched
-CODEOWNERS with the frozen module page's owners or required reviewers and
-documented governance expertise; propose one to three focused reviewers with an
-explicit contract rationale.
-
-Identifying or suggesting reviewers is read-only. Requesting reviewers or
-posting `@mention` comments changes external state and requires explicit user
-authorization. When authorized, recheck the head, deduplicate existing
-requests, and post at most one consolidated comment. Do not infer this
-permission from a request to review the code.

.claude/skills/review-pr/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "vLLM-Omni PR Review"
-  short_description: "Review vLLM-Omni PRs and route owner requests"
-  default_prompt: "Use $review-pr to review this vLLM-Omni pull request with owner-specific rules and evidence-backed findings."

.claude/skills/review-pr/references/checks/model-addition-checklist.md

@@ -1,121 +0,0 @@
-# Model Addition Checklist
-
-Read this reference when a PR adds or expands a model architecture, pipeline,
-loader, processor, registry entry, or stage configuration.
-
-Official docs: [model contribution guides](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/model/),
-[adding an omni model](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/model/adding_omni_model/),
-[adding a diffusion model](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/model/adding_diffusion_model/),
-[adding a TTS model](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/model/adding_tts_model/),
-[supported models](https://docs.vllm.ai/projects/vllm-omni/en/latest/models/supported_models/),
-[diffusion features](https://docs.vllm.ai/projects/vllm-omni/en/latest/user_guide/diffusion_features/),
-and [feature compatibility](https://docs.vllm.ai/projects/vllm-omni/en/latest/user_guide/feature_compatibility/).
-
-## Match claims to the diff
-
-- Reconcile every claimed architecture, modality, variant, feature, and example
-  with changed files and registry entries.
-- Resolve config model types, architecture names, callable paths, exports, and
-  dependency extras against live symbols.
-- Check sibling generations sharing an architecture name are disambiguated by
-  a stable config predicate rather than import order or an accidental default.
-
-## Close the integration chain
-
-Trace:
-
-```text
-public model id -> config/pipeline selection -> registry -> loader/processor
-  -> stage inputs -> model execution -> stage/public output
-```
-
-Verify optional dependencies fail with an actionable message, weight names and
-dtypes map correctly, and each advertised serving mode reaches the production
-dispatcher. Confirm outputs are non-empty and valid for their modality, shape,
-sample rate, or response schema.
-
-## Keep support documentation truthful
-
-- Build an evidence-backed inventory of the new model's exact architecture and
-  checkpoint identifiers, modalities and tasks, hardware backends, serving
-  modes, and supported acceleration, parallelism, cache, offload, and
-  quantization features. Treat untested support as unknown, not supported.
-- Update `docs/models/supported_models.md` with the architecture, model family,
-  example checkpoints, and only the backends validated by the PR.
-- For a diffusion model, add it to the applicable ImageGen, VideoGen, or
-  AudioGen table in `docs/user_guide/diffusion_features.md`. Fill every feature
-  column according to its legend and document partial support or constraints.
-- Update `docs/user_guide/feature_compatibility.md` when the model changes valid
-  feature combinations, configuration constraints, examples, or limitations,
-  and update any other branch-local support table affected by the claims.
-- Cross-check every documented support mark against the registry, configuration,
-  production-path tests, and PR evidence; do not copy a sibling model's support
-  claims without validation.
-
-## Ship the model recipe
-
-- Require every new model PR to add or update one model-family recipe under
-  `recipes/<vendor>/` and its row in the `recipes/README.md` Available Recipes
-  table. Follow [`recipes/TEMPLATE.md`](../../../../../recipes/TEMPLATE.md) and
-  the layout rules in
-  [`recipes/README.md`](../../../../../recipes/README.md); the
-  external recipes repository is a structural reference, not a substitute.
-- Include only tested task, serving-mode, and hardware configurations. Keep the
-  exact model identifiers, flags, commands, verification, feature support,
-  constraints, and limitations consistent with code, tests, examples, and the
-  support documentation.
-- Cover each validated platform in its own hardware section. Use one recipe per
-  model family by default; justify a split when configurations cannot be kept
-  clear in one file, and do not add placeholder sections for untested platforms.
-
-## Compare the reference implementation
-
-Require every new model PR to include a head-versus-reference accuracy or
-quality and performance comparison:
-
-- Name the canonical implementation and pin its repository revision, package
-  version, configuration, and checkpoint. If it cannot run, explain why and use
-  the closest runnable reference; do not silently omit the comparison.
-- Match inputs or dataset, seed, output settings, precision or quantization,
-  hardware, software, warmup, repetitions, synchronization, and timing and
-  memory scope. Include exact commands and environment details for both sides.
-- Compare accuracy or output quality with a task-appropriate metric and explicit
-  tolerance. When no reliable metric exists, provide paired fixed-input outputs,
-  artifacts, and evaluation criteria, and explain expected numerical or
-  qualitative differences.
-- Report end-to-end latency, task-appropriate throughput, peak device memory,
-  run-to-run variability, and head/reference ratios at equivalent output quality.
-- Prefer a timing split for preprocessing or encoding, each model stage,
-  inter-stage transfer or communication, decoding or postprocessing, and output
-  assembly. Define the boundaries, account for overlap, reconcile the split with
-  end-to-end time, and explain any unavailable stage measurement.
-
-Use [perf-verification.md](perf-verification.md) for the comparison protocol and
-repository benchmark and profiling links.
-
-## Remove accidental surface
-
-Search bounded call sites for:
-
-- inference-dead training `forward()` paths, unused factories/wrappers, never-set
-  branch keys, and immediately discarded parameters;
-- duplicate payload strings, validation, or shape coercion across stages;
-- compatibility aliases in brand-new code without an existing caller;
-- private symbols re-exported as public API or module-level side effects.
-
-Keep code only when it has a distinct live caller, invariant, or compatibility
-contract. Prefer one typed producer-consumer schema to repeated string keys.
-
-## Require proportionate evidence
-
-- Run a representative production-path inference and assert output content, not
-  only process survival.
-- Require profiling or A/B tables when the PR makes performance, memory,
-  precision, or quality claims, or when a suspected hot-path/device bug needs
-  that evidence. Do not impose fixed utilization or regression thresholds that
-  the repository does not define.
-- Require focused registry/config/loading tests, a representative E2E path, and
-  user-facing model/usage documentation.
-
-Use [diffusion.md](../modules/diffusion.md) for diffusion models and
-[perf-verification.md](perf-verification.md) for quantitative claims.

.claude/skills/review-pr/references/checks/perf-verification.md

@@ -1,51 +0,0 @@
-# Performance and Accuracy Verification
-
-Activate this reference when the PR adds a model or claims or intentionally
-changes latency, throughput, memory, scaling, precision, or output quality.
-
-Official docs: [profiling](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/profiling/),
-[serving benchmarks](https://docs.vllm.ai/projects/vllm-omni/en/latest/cli/bench/serve/),
-and [metrics](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/metrics/).
-
-## Comparable A/B contract
-
-Compare frozen base and head for an existing path. For a new model absent from
-base, compare head with a pinned canonical reference implementation. Use the same:
-
-- hardware, driver, software versions, model/checkpoint, and dependencies;
-- input or dataset, seed, precision, batch/concurrency, topology, and feature
-  flags;
-- warmup, measured repetitions, synchronization, timing scope, and memory
-  collection method.
-
-Keep exact commands and report variability rather than a cherry-picked run.
-Use the repository's benchmark when it covers the claim; otherwise use the
-smallest reproducible workload that reaches the changed production path.
-
-## Evidence table
-
-| Dimension | Typical evidence |
-| --- | --- |
-| Latency | End-to-end latency and, when available, TTFT plus a defined per-stage and transfer-time split. |
-| Throughput/scaling | Requests, tokens, frames, or audio duration per second across the claimed concurrency/topology. |
-| Memory | Peak allocated/reserved device memory and OOM boundary if relevant. |
-| Quality/accuracy | Repository metric or known-good output comparison with an explicit tolerance; paired samples when no metric exists. |
-
-Every optimization needs correctness or quality evidence. A faster result on a
-different workload, precision, seed, or topology is not a valid comparison.
-
-## Reviewer verification ladder
-
-1. Run base/head A/B on suitable hardware when affordable.
-2. If only one side can run, verify the script and request a comparable pair.
-3. If hardware or assets are unavailable, audit methodology, code path, and
-   contributor evidence; name the exact unverified claim.
-
-Classify discrepancies before reporting: implementation regression, benchmark
-bug, environmental drift, noise, or unsupported claim. Explain material
-regressions against the PR's stated goal or repository contract; do not invent
-universal percentage thresholds.
-
-Report claimed and measured values together, bind them to the frozen SHAs and
-environment, and keep unavailable hardware as a validation gap rather than a
-fabricated pass.

.claude/skills/review-pr/references/checks/test-quality-evaluation.md

@@ -1,39 +0,0 @@
-# Test Quality Evaluation
-
-Read this reference when tests change, a risky production path has no test, or
-a test-only PR may not prove the intended behavior.
-
-Official docs: [test system overview](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/test_system_overview/)
-and [test writing guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/test_writing_guide/).
-
-## Static proof check
-
-For each changed semantic path, ask whether the test would fail if that behavior
-were reverted or broken. Check:
-
-- assertions pin the contract, not only non-null output, logs, or “no crash”;
-- the production dispatcher, registry, connector, or scheduler is reached
-  instead of the changed behavior being mocked away;
-- fakes preserve relevant types, MRO, shapes, devices, async behavior, and
-  lifecycle transitions;
-- seeds, ordering, timing, synchronization, external services, and numeric
-  tolerances are deterministic or explicitly controlled;
-- normal, invalid, boundary, feature-off, failure/cancellation, and regression
-  paths are covered where the diff changes them;
-- run-level and domain markers place hardware/model tests in the intended CI
-  lane without silently skipping the contract.
-
-Map source symbols to tests with bounded `rg` searches; do not assume the test
-tree mirrors production paths.
-
-## Runtime check
-
-Run the narrowest affected tests supported by the environment. Record skipped
-hardware/model cases as gaps. Classify failures as code, test, infrastructure,
-or flaky before turning them into findings; one passing rerun does not erase a
-flakiness signal.
-
-Keep grades or matrices internal. Report only concrete code bugs or the one or
-two test defects that leave changed behavior materially unprotected. Use
-[tests-docs-checklist.md](tests-docs-checklist.md) for CI and documentation
-coverage.

.claude/skills/review-pr/references/checks/tests-docs-checklist.md

@@ -1,48 +0,0 @@
-# Tests and Documentation Checklist
-
-Use this reference to connect changed behavior to coverage, CI selection,
-examples, documentation, and reproducible PR evidence.
-
-Official docs: [test writing guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/test_writing_guide/),
-[test execution guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/test_execution_guide/),
-and [documentation guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/DOCS_GUIDE/).
-
-## Coverage packet
-
-For each high-risk change, record a compact internal packet:
-
-```text
-change and failure risk -> existing unit/E2E coverage -> uncovered boundary
-  -> smallest test and stable assertion that closes the gap
-```
-
-Prefer a regression test that fails on the frozen base for bug fixes. Check
-numeric tolerances, deterministic inputs, realistic mocks, hardware/domain
-markers, and Buildkite/CI wiring using the documentation present on the reviewed
-branch. A skipped test is not a pass.
-
-## Documentation sync
-
-Require user-facing updates when the diff changes a model, feature, CLI/API,
-config key, default, compatibility behavior, or supported platform. Verify:
-
-- the actual docs navigation and support tables used by the branch;
-- exact identifiers, defaults, constraints, known limitations, and migration;
-- a minimal runnable example for newly exposed behavior;
-- examples and docs agree on commands, parameters, output schema, and supported
-  modes;
-- links and the bounded live contract build or resolve correctly.
-
-Do not request docs for internal behavior with no user-visible contract.
-
-## PR evidence
-
-For contributor-run tests or benchmarks, require enough provenance to evaluate
-the claim: hardware, relevant software versions, exact commands, inputs/model,
-result, and approximate runtime. Performance or accuracy evidence must compare
-base and head under equivalent conditions; use
-[perf-verification.md](perf-verification.md).
-
-Turn a missing test or document into a finding only when it protects or explains
-changed behavior. Name the smallest useful addition rather than requesting a
-broad coverage expansion.

.claude/skills/review-pr/references/checks/verification.md

@@ -1,36 +0,0 @@
-# Active Verification
-
-Read this reference when a runnable affected path and suitable local or remote
-hardware are available. Never claim device evidence from static analysis or a
-simulated backend.
-
-Official docs: [installation](https://docs.vllm.ai/projects/vllm-omni/en/latest/getting_started/installation/)
-and [test execution guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/test_execution_guide/).
-
-## Choose the narrowest level
-
-| Available environment | Verification |
-| --- | --- |
-| Matching accelerator, model/assets, and server | Targeted unit/integration test plus one representative E2E request. |
-| Matching accelerator without serving setup | Targeted model/runtime test and output or metric inspection. |
-| CPU/static environment only | Import/version preflight, focused CPU tests, config/registry resolution, and static contract checks. |
-| Missing dependencies or inaccessible hardware | Record the exact gap and evaluate contributor/CI evidence. |
-
-## Execute safely
-
-1. Bind the run to the frozen head SHA and record Python, platform, dependency,
-   model, device, and relevant environment fingerprints.
-2. Run the smallest affected unit test before an E2E workload.
-3. Exercise the changed public or production-dispatch path with bounded inputs.
-4. Compare actual output, metrics, cleanup, and exit behavior with the PR claim.
-5. For base/head claims, use the equivalent A/B protocol in
-   [perf-verification.md](perf-verification.md).
-
-Avoid disturbing shared servers, ports, models, or accelerators without user
-authorization. Do not install large dependencies, download gated assets, or
-start remote workloads merely because hardware might exist.
-
-Report the command, environment, result, and any skipped path. Classify failures
-as change-induced, pre-existing, infrastructure, environment, or flaky before
-making a finding. A hardware gap lowers confidence; it is not automatic proof
-of a defect.

.claude/skills/review-pr/references/delivery/maintainer-style-study.md

@@ -1,105 +0,0 @@
-# Maintainer Review Style
-
-Use this reference only when turning proved findings into comments. The baseline
-maintainer samples favor short, direct comments and reserve long explanations
-for architecture or non-obvious failure paths.
-
-Official docs: [contributing and review process](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/).
-
-## Evidence basis
-
-This calibration used 928 PRs merged from 2026-05-10 through 2026-08-08.
-Candidates were ranked by substantive human inline-review threads, then by
-distinct reviewers and review rounds. Author self-comments, bots and AI
-reviewers, and bodyless approvals were excluded. Counts selected the sample;
-the practices below came from reading root comments and follow-up replies.
-
-The main set contains the six leaders after filtering; three other high-ranked
-PRs add core-runtime and benchmark coverage. All were merged.
-
-| PR | Review boundary |
-| --- | --- |
-| [#2906](https://github.com/vllm-project/vllm-omni/pull/2906) | New TTS model, shared utilities, recipes, and request state. |
-| [#3907](https://github.com/vllm-project/vllm-omni/pull/3907) | Full-duplex API, session lifecycle, concurrency, and realtime evidence. |
-| [#2162](https://github.com/vllm-project/vllm-omni/pull/2162) | Diffusion world model, OpenPI serving, tests, examples, and docs. |
-| [#3454](https://github.com/vllm-project/vllm-omni/pull/3454) | Diffusion model, generic CLI surface, loaders, and configuration scope. |
-| [#4425](https://github.com/vllm-project/vllm-omni/pull/4425) | Structured configuration, typing, defaults, and compatibility. |
-| [#5397](https://github.com/vllm-project/vllm-omni/pull/5397) | Distributed offload, collectives, failure handling, and load semantics. |
-| [#4281](https://github.com/vllm-project/vllm-omni/pull/4281) | Composable parallelism, configuration contracts, and examples. |
-| [#3628](https://github.com/vllm-project/vllm-omni/pull/3628) | Stage metrics, benchmark definitions, opt-in API behavior, and cleanup. |
-| [#3855](https://github.com/vllm-project/vllm-omni/pull/3855) | Stage runtime, thread safety, startup, and compatibility. |
-
-Historical comments calibrate delivery; they do not create merge policy. Live
-code, tests, repository docs, and the current `CODEOWNERS` file remain
-authoritative. When refreshing this study, promote a practice only when it
-recurs across at least three PRs or is supported by current repository guidance.
-
-## Recurring review behavior
-
-- Start from a changed contract, not a style preference. State the exact
-  request, configuration, topology, or failure path that triggers the issue.
-- Protect repository boundaries. Keep model-specific behavior in its domain,
-  move genuinely reusable logic to a shared module, and reuse existing loaders,
-  protocols, definitions, and config sources instead of bypassing them.
-- Challenge unrelated scope and abstractions. Ask why a new flag, config, class,
-  helper, fallback, or file is needed when an existing path appears sufficient.
-- Trace concurrency and terminal paths: overlapping requests, disconnect,
-  cancellation, partial failure, stale replies, collective schedule mismatch,
-  cleanup, and retry. Prefer an explicit startup error for unsupported
-  combinations over silently running with incomplete state or wrong weights.
-- Preserve user-visible behavior across variants. An accepted CLI/API/config
-  field must be applied, explicitly rejected, or visibly warned about; compare
-  normal and headless, offline and online, and streaming and non-streaming paths.
-- Ask for evidence at the affected boundary: a regression test using the real
-  tensor or protocol shape, correct pytest markers so CI runs it, comparable A/B
-  performance results, or an SLO-oriented latency/quality measurement.
-- Keep interfaces explicit: avoid `Any` and opaque strings where a precise
-  union, enum, or typed envelope exists; remove dead code and duplicated
-  constants; validate requests before expensive execution.
-- Document module scope and non-obvious invariants. Update examples, recipes,
-  supported-model/feature docs, and hardware assumptions when users rely on
-  them.
-- When expertise crosses an ownership boundary, ask a named owner to inspect a
-  specific file or contract and explain why. Do not send a generic `PTAL` list.
-- Keep non-blocking cleanup in a linked follow-up only after the current PR is
-  safe. If a revision fixes only part of a failure chain, continue the existing
-  thread with the remaining trigger instead of opening a duplicate finding.
-
-## Write the finding
-
-- Lead with the issue or decisive question; omit a review preamble.
-- Name the concrete trigger and impact, then the smallest fix direction.
-- Keep obvious fixes to one sentence. Use more detail only when the call path or
-  ownership boundary is otherwise unclear.
-- Prefer one root-cause comment over repeated symptom comments.
-- Hedge only when evidence is genuinely incomplete; mark that item as a
-  question or validation gap rather than overstating severity.
-- Say briefly that no findings were found when the review is clean; zero
-  comments is a valid outcome when posting is authorized.
-
-Useful forms:
-
-```text
-This leaves <state> allocated when <failure/cancellation path>. Release it in
-the shared terminal cleanup path.
-```
-
-```text
-Does this producer also update <consumer>? It still reads the old field here.
-```
-
-```text
-With <configuration>, this bypasses <existing loader/validator>, so <impact>.
-Reuse that path or reject this combination before startup.
-```
-
-```text
-@<owner>, could you check <specific boundary>? This changes <contract> used by
-<consumer>.
-```
-
-Use a priority label only for a proved high-impact defect. Avoid generic praise,
-routine “Nit:” prefixes, decorative severity labels, audit templates, rule IDs,
-comment-count narration, and “I left a few comments.” Keep approvals, review
-events, reviewer requests, mentions, and GitHub replies subject to the user's
-explicit authorization.

.claude/skills/review-pr/references/delivery/review-requests.md

@@ -1,99 +0,0 @@
-# Focused Code-Owner Review Requests
-
-Read only when the user asks to identify, suggest, request, add, or ping
-reviewers. Finding candidates is read-only; GitHub review requests and
-`@mention` comments are external writes.
-
-Owner sources, in order:
-
-1. the reviewed head's
-   [CODEOWNERS](https://github.com/vllm-project/vllm-omni/blob/main/.github/CODEOWNERS)
-   for path ownership;
-2. the active module design page's `owners` and `required_reviewers` metadata
-   for contract ownership and mandatory design review; and
-3. documented
-   [governance expertise](https://docs.vllm.ai/projects/vllm-omni/en/latest/community/governance/)
-   for specialization and tie-breaking.
-
-Resolve all three from the reviewed head when available because ownership
-changes over time. Use published docs only to discover a page absent from an
-older checkout, never to override the frozen head, and do not copy a static
-owner list into review output. CODEOWNERS remains the path authority; module
-metadata identifies contract experts and required design reviewers.
-
-## Rank candidates
-
-1. Freeze the PR head and collect changed files, author, requested reviewers,
-   submitted reviews, and existing comments.
-2. Resolve the **last matching CODEOWNERS rule** for each changed file. Do not
-   union an earlier broad rule with a later specific rule.
-3. Resolve the primary module and feature overlays through
-   [design-contracts.md](../process/design-contracts.md). Read the active module
-   page's status, `owners`, and `required_reviewers`; do not treat owners on an
-   archived, superseded, or unrelated page as current authority.
-4. Group files by the selected primary owner and the exact module or feature
-   contract needing review. Weight production owners and live consumers above
-   tests/docs/CI owners and the repository-wide fallback. Include an applicable
-   `required_reviewers` entry even when it is not the path owner, and label why.
-5. Use documented governance specialties only to choose among matching owners:
-   for example serving versus configuration, diffusion model versus cache or
-   parallelism, TTS versus generic model execution, or CI versus tests.
-6. Exclude the PR author, bots, users who already completed the needed review,
-   and duplicate pending requests. Do not infer availability or invent
-   expertise from a username.
-7. Select one reviewer for a single-owner change and at most three for a real
-   cross-module change. If more are plausible, rank them but do not ping a
-   broad group; ask the user before exceeding three.
-
-If every specific owner is excluded, consider one repository-wide fallback
-owner and label that choice as a fallback rather than a path match. Never fan
-out to the full fallback list. Prefer a qualified owner who covers multiple
-critical path groups over separate reviewers for each file. If CODEOWNERS is
-missing or invalid, state that gap and use governance only as a labeled fallback.
-
-Recent file history may break a tie only when CODEOWNERS and governance remain
-ambiguous. Never use commit count alone to override an explicit current owner.
-
-## Preview before writing
-
-Show the user the exact candidate set and rationale:
-
-```text
-@owner — <owned paths or module role>; please verify <specific module or feature contract>.
-```
-
-Draft one consolidated comment tied to the frozen head:
-
-```text
-Requesting focused review for `<short-head-sha>`:
-
-- @owner1: could you check the <module contract> in `<path/group>`?
-- @owner2: could you check the <feature or cross-boundary contract> in `<path/group>`?
-
-Relevant validation: <one concise result or exact remaining gap>.
-```
-
-Mention only owners being requested. Keep the reason specific enough that each
-person knows what decision or invariant needs attention; do not post a generic
-“please review” or a generated ownership audit.
-
-## External-write gate
-
-- “Who should review?”, “suggest reviewers”, or “draft a request” authorizes
-  only the preview.
-- “Request/add these reviewers” authorizes the GitHub review-request mutation.
-- “Ping/comment/tag the owners” authorizes the consolidated comment.
-- When the user explicitly asks to request reviews **with an owner comment**,
-  both writes are authorized. Obey narrower wording when only one action is
-  requested.
-
-Immediately before an authorized write, verify the PR is still open, the head
-SHA is unchanged, and the candidate is not the author or already satisfied.
-Report draft/WIP state and avoid notifications unless the user explicitly wants
-reviewers requested before ready-for-review.
-
-Use the GitHub connector for reviewer requests and the single top-level comment;
-use `gh` only when connector coverage is unavailable. Do not submit an approval,
-request-changes event, label, assignment, or multiple comments as part of this
-action. After writing, reread the PR and report the reviewers requested and the
-comment URL. If the head changed, discard the draft and rerank before posting.

.claude/skills/review-pr/references/features/communication.md

@@ -1,24 +0,0 @@
-# Communication Features
-
-Use with the OmniConnector, stage-runtime, configuration, and I/O module
-contracts. Load the concrete backend design from the reviewed head:
-
-| Backend | Design |
-| --- | --- |
-| Mooncake store | [MooncakeStoreConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/mooncake_store_connector/) |
-| Mooncake transfer engine | [MooncakeTransferEngineConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/mooncake_transfer_engine_connector/) |
-| Mori transfer engine | [MoriTransferEngineConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/mori_transfer_engine_connector/) |
-| Shared memory | [SharedMemoryConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/shared_memory_connector/) |
-| Yuanrong store | [YuanrongConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/yuanrong_connector/) |
-| Yuanrong transfer engine | [YuanrongTransferEngineConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_connectors/yuanrong_transfer_engine_connector/) |
-
-## Feature checks
-
-- Verify dependency, service, device/network, port, memory-pool, and environment
-  prerequisites with actionable startup errors.
-- Match key/metadata construction, sender and receiver roles, allocation,
-  ownership, completion, and supported fast/serialized paths.
-- Exercise timeout, retry, stale sender/buffer reclamation, partial transfer,
-  cancellation, and connector close semantics.
-- Validate the smallest supported same-host or cross-node topology and document
-  backend limitations and operational diagnostics.

.claude/skills/review-pr/references/features/diffusion-acceleration.md

@@ -1,26 +0,0 @@
-# Diffusion Acceleration Features
-
-Use with the exact diffusion submodule plus platform, cache, quantization, or
-benchmarking contracts selected by the live path.
-
-| Feature family | Designs |
-| --- | --- |
-| Parallelism | [CFG](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/cfg_parallel/), [Expert](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/expert_parallel/), [HSDP](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/hsdp/), [Pipeline](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/pipeline_parallel/), [Sequence](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/sequence_parallel/), [Tensor](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/tensor_parallel/), [VAE patch](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/vae_parallel/) |
-| Attention | [Skip-Softmax](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/skip_softmax/) |
-| Quantization | [Quantization](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/quantization/) |
-| Cache | [Cache-DiT](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/cache_dit/), [TeaCache](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/teacache/) |
-| Batching | [Diffusion Continuous Batching](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/diffusion_continuous_batching/) |
-| Offload | [Distributed Layerwise Offload](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/distributed_layerwise_offload/) |
-
-## Feature checks
-
-- Verify feature selection, supported models/platforms/topologies, defaults,
-  dependencies, and every touched feature combination.
-- Preserve feature-off and single-rank correctness; reject unsupported
-  combinations before collectives, loading, or execution begin.
-- Trace shapes, shards, ranks, collectives, precision, cache validity, residency,
-  and per-request state through the selected runtime hooks.
-- Compare output quality or accuracy against the disabled/reference path before
-  accepting latency or memory improvements.
-- Require exact commands, topology, environment, warmup, repetitions, and
-  measurements for performance claims; update feature compatibility docs.

.claude/skills/review-pr/references/features/infrastructure-performance.md

@@ -1,22 +0,0 @@
-# Infrastructure and Performance Features
-
-Load the matching design from the reviewed head:
-
-- [Prometheus Metrics](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/metrics/)
-  for logger wrapping, gating, lifecycle, stage transfer, and metric definitions.
-- [Speech Generation Performance Optimizations](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/qwen3_omni_tts_performance_optimization/)
-  for stage batching, CUDA graphs, async chunk, streaming, re-prefill, compile,
-  and deployment evidence.
-
-## Feature checks
-
-- Route instrumentation changes through observability or profiling and result
-  methodology through benchmarking and the performance evidence check.
-- Preserve opt-in/default behavior, units, labels, aggregation, timing scope,
-  lifecycle resets, and bounded overhead.
-- For stacked optimizations, measure each increment against the same baseline
-  and explain interactions, quality guards, regressions, and limitations.
-- Require exact model, checkpoint, hardware, software, workload, topology,
-  concurrency, warmup, repetitions, and production commands.
-- Update the design page when metric meaning, supported optimization stack, or
-  deployment guidance changes.

.claude/skills/review-pr/references/features/runtime-stage-execution.md

@@ -1,24 +0,0 @@
-# Runtime and Stage Execution Features
-
-Load the matching design from the reviewed head:
-
-| Feature | Design | Primary module intersections |
-| --- | --- | --- |
-| Disaggregated inference | [Design](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/disaggregated_inference/) | Configuration, stage runtime, OmniConnector, I/O contracts |
-| Async chunk | [Design](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/async_chunk/) | Model integration, orchestration, stage runtime, connector, I/O |
-| Async diffusion output | [Design](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/async_diffusion_output/) | Diffusion runtime, I/O contracts, entrypoints |
-| Async Omni output materialization | [Design](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/omni_async_output_materialization/) | AR runtime, model integration, I/O contracts, orchestration |
-| Automatic prefix caching | [Design](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/feature/prefix_caching/) | AR runtime, cache management, I/O contracts |
-
-## Feature checks
-
-- Confirm the feature's supported models, entrypoints, stage types, topology,
-  configuration, default, and compatibility limitations.
-- Trace enablement from public/config ingress through every participating module
-  and verify the advertised production dispatch actually selects it.
-- Preserve a correct disabled or fallback path and make unsupported combinations
-  fail or warn as documented.
-- Test overlap, ordering, identity, backpressure, cancellation, failure, final
-  partial output, and cleanup at each asynchronous boundary.
-- Update the feature page, support matrices, examples, and recipes when behavior
-  or coverage changes.

.claude/skills/review-pr/references/modules/ar-runtime.md

@@ -1,22 +0,0 @@
-# Autoregressive Runtime
-
-Primary design: [Autoregressive Runtime](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/ar_runtime/).
-
-Use for AR request queues, scheduling state, token and memory budgets, KV/input
-readiness, workers, runners, and upstream vLLM request/cache transitions.
-
-## Contract checks
-
-- Preserve upstream request-state, scheduling, cache, and preemption semantics
-  unless an Omni-specific difference is documented and tested.
-- Convert modality-specific data through explicit input or output adapters; do
-  not inject it through unrelated scheduler state.
-- Keep workers and model runners focused on assigned execution rather than
-  admission or cross-stage routing.
-- Synchronize token, sequence, batch, and memory budgets with worker-visible
-  state and prevent starvation, double counting, or stale readiness.
-- Preserve legal transitions and one terminal cleanup path across completion,
-  abort, timeout, preemption, worker failure, and shutdown.
-
-Test request lifecycle, scheduling decisions, abort, cache state, adapters, and
-every affected worker execution mode against the pinned upstream contract.

.claude/skills/review-pr/references/modules/benchmarking.md

@@ -1,24 +0,0 @@
-# Benchmarking
-
-Primary design: [Benchmarking](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/benchmarking/).
-
-Use when benchmark code, workloads, metric calculations, CLI benchmark
-entrypoints, or result metadata change. Use the performance check separately
-when a PR uses benchmark results as evidence.
-
-## Contract checks
-
-- Record model and revision, code SHA, hardware, software, configuration,
-  workload, precision, topology, concurrency, warmup, repetitions, and
-  measurement window.
-- Validate successful and semantically acceptable outputs before accepting
-  timing, memory, or scaling results.
-- Define every metric's unit, population, aggregation, synchronization, and
-  timing scope.
-- Keep workload parsing and metric computation deterministic and reusable
-  across base and head.
-- Reject comparisons that change material workload or runtime settings without
-  isolating and explaining that difference.
-
-Test workload parsing and metric calculations with deterministic fixtures and
-publish exact commands plus variability for quantitative claims.

.claude/skills/review-pr/references/modules/cache-management.md

@@ -1,22 +0,0 @@
-# Cache Management
-
-Primary design: [Cache Management](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/cache_management/).
-
-Use for AR or diffusion cache identity, reusable state, validity, lifecycle,
-reset, eviction, and teardown.
-
-## Contract checks
-
-- Include every model, request, input, timestep, precision, device, topology,
-  and feature property that can change a reused value in cache identity.
-- Preserve a correct disabled and miss path; never reuse after validity inputs
-  change.
-- Isolate request-scoped state across concurrent requests and define ownership
-  for model-scoped state.
-- Make reset, invalidation, eviction, capacity, and teardown explicit on
-  completion, cancellation, failure, model reload, and shutdown.
-- Keep cache optimizations behind the owning runtime's hooks rather than adding
-  a second request lifecycle.
-
-Test hit, miss, invalidation, disabled behavior, concurrency, capacity, reset,
-and teardown, with quality comparison when reuse is approximate.

.claude/skills/review-pr/references/modules/configuration.md

@@ -1,24 +0,0 @@
-# vLLM-Omni Configuration
-
-Primary design: [vLLM-Omni Configuration](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/vllm_omni_config/).
-
-Use for config construction, deploy YAML, registries, schema, defaults,
-aliases, CLI projection, stage config, and topology. Inspect the reviewed
-page's status: while its contract remains deferred or draft, current code and
-tests—not proposed precedence rules—are authoritative.
-
-## Contract checks
-
-- Resolve each supported structured, legacy, CLI, environment, default, alias,
-  and stage-override producer through its actual runtime consumer.
-- Reject unknown or owner-mismatched fields explicitly; keep process-local
-  runtime objects out of transportable configuration.
-- Verify default, explicit, and feature-off values reach every live factory and
-  consumer without silent reinterpretation.
-- Treat stage count, placement, connector, parallelism, device, and memory
-  fields as one topology contract and reject impossible combinations early.
-- Preserve supported construction-path parity until a documented migration
-  removes a path.
-
-Require normalization and schema tests, a live-consumer assertion, and docs for
-public keys, defaults, constraints, precedence, or migration behavior.

.claude/skills/review-pr/references/modules/diffusion.md

@@ -1,33 +0,0 @@
-# Diffusion Module Family
-
-Primary design: [Diffusion Modules](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/).
-
-Use for diffusion-stage behavior, then load the exact submodule page from the
-reviewed head:
-
-| Submodule | Signals | Design |
-| --- | --- | --- |
-| Runtime | Admission, scheduling, execution, progress, outputs, cancellation, hooks, cleanup | [Diffusion Runtime](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/diffusion_runtime/) |
-| Model Integration | Pipelines, registry, loader, adapters, shared layers, model-specific processing | [Diffusion Model Integration](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/diffusion_model_integration/) |
-| Continuous Batching | Compatibility, request/step batches, per-request progress, capacity | [Continuous Batching](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/continuous_batching/) |
-| Parallelism | Rank topology, process groups, sharding, collectives, distributed execution | [Parallelism](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/parallelism/) |
-| Offloader | Residency, transfers, memory accounting, prefetch, teardown | [Offloader](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/diffusion/offloader/) |
-
-## Family-wide checks
-
-- Keep one scheduler-owned lifecycle from admission through completion,
-  cancellation, failure, and cleanup; optional features must use defined hooks.
-- Select pipelines through registry and loader contracts instead of scattered
-  model-name conditionals; keep genuine model differences in model directories.
-- Trace latent, conditioning, timestep, generator, shape, layout, dtype, device,
-  batch expansion, and output conversion through the actual consumer.
-- Make batch compatibility and per-request isolation explicit; never associate
-  output by unstable batch position.
-- Derive topology from validated configuration, define every sharding boundary,
-  keep collectives symmetric, and preserve a supported single-rank path.
-- Track one residency owner per offloaded component, wait for transfer readiness,
-  preserve model state, bound retained copies, and clean up deterministically.
-
-Load matching feature designs for cache, quantization, parallelism, continuous
-batching, or offload. Require feature-off correctness, representative inference,
-terminal-path tests, and quality evidence for optimizations.

.claude/skills/review-pr/references/modules/engine-orchestration.md

@@ -1,23 +0,0 @@
-# Engine Orchestration
-
-Primary design: [Engine Orchestration](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/engine_orchestration/).
-
-Use for request-state creation, cross-stage routing, output ordering, companion
-tracking, RPC correlation, cancellation propagation, and terminal convergence.
-Orchestration does not own replica placement, stage-process startup, public
-rendering, connector transport, or payload and error schemas.
-
-## Contract checks
-
-- Keep one owner for cross-stage routing; entrypoints, models, and stage clients
-  must not independently select the next logical stage.
-- Preserve request identity and output order across concurrent stages and
-  correlate every control or RPC result to the originating request and wave.
-- Make terminal state monotonic: no new forwarding after success, abort,
-  request failure, or fatal engine failure.
-- Propagate cancellation and failure to every active stage and release
-  orchestrator-owned tasks, queues, companions, and request state.
-- Preserve shutdown ordering across the orchestrator and stage runtime.
-
-Test representative multi-stage routing, ordering, correlation, cancellation,
-failure, and repeated shutdown.

.claude/skills/review-pr/references/modules/entrypoints.md

@@ -1,25 +0,0 @@
-# Entrypoints and Serving Boundaries
-
-Primary design: [Entrypoints and Serving Boundaries](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/entrypoints/).
-
-Use for offline APIs, CLI and server composition, OpenAI-compatible routes,
-request validation, response conversion, streaming, sessions, and engine
-handoff. Entrypoints adapt public contracts; they do not own cross-stage
-routing, stage lifecycle, configuration precedence, payload schemas, or error
-classification.
-
-## Contract checks
-
-- Normalize and validate public values once before engine submission.
-- Preserve request identity, modality, ordering, and exactly one terminal event
-  across streaming, disconnect, cancellation, and failure.
-- Translate internal outputs and errors explicitly for each advertised offline,
-  HTTP, SSE, WebSocket, or asynchronous-job path.
-- Keep model-specific behavior behind a common adapter or processor instead of
-  adding model-name policy to generic entrypoints.
-- Require API or CLI changes to explain necessity, alternatives, compatibility,
-  migration, and the supported route or transport matrix.
-
-Test the affected public protocol, normalization, engine handoff, rendering,
-and terminal outcomes. Route orchestration, I/O schema, and semantic error
-changes to their module contracts.

.claude/skills/review-pr/references/modules/error-contracts.md

@@ -1,24 +0,0 @@
-# Error Classification, Propagation, and Rendering
-
-Primary design: [Error Classification, Propagation, and Rendering](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/error_contracts/).
-
-Use when a change classifies failures, crosses process boundaries, decides
-fatal versus request-scoped impact, sanitizes context, or renders offline,
-HTTP, SSE, WebSocket, or asynchronous-job errors. The I/O module owns the wire
-schema; this module owns the meaning of its error fields.
-
-## Contract checks
-
-- Keep request-scoped failure isolated unless the underlying engine is no
-  longer usable.
-- Preserve stable classification and request context across process and
-  protocol boundaries without exposing prompts, outputs, secrets, or internal
-  stack details.
-- Keep cancellation distinguishable from internal failure.
-- Terminate each public transport exactly once with consistent status, body,
-  event, finish reason, and metrics classification.
-- Maintain compatibility across mixed or older producers only when the
-  reviewed contract defines that behavior.
-
-Test table-driven classification, wire round trips, fatal/request-scoped
-propagation, cancellation, sanitization, and every affected public renderer.

.claude/skills/review-pr/references/modules/execution-platforms.md

@@ -1,23 +0,0 @@
-# Execution Platforms
-
-Primary design: [Execution Platforms](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/execution_platforms/).
-
-Use for hardware capability detection, worker selection, patches, kernels,
-attention backends, and vendor-specific configuration or connectors.
-
-## Contract checks
-
-- Guard hardware behavior through platform selection or capability detection
-  and fail clearly when unsupported.
-- Keep portable modules free of direct vendor imports when a common selector
-  exists; verify portable imports without the target accelerator.
-- Override only behavior that differs from common or upstream implementations,
-  and compare sibling worker hooks when inheritance does not provide parity.
-- Preserve dtype, layout, rank, stream, synchronization, workspace,
-  graph-capture, and resource-lifetime contracts.
-- Do not let simplified CPU doubles hide platform MRO, initialization, or
-  dispatch failures.
-
-Run portable checks first, then the smallest matching-device test in a fresh
-environment. Report unavailable hardware as a validation gap, never simulated
-device evidence.

.claude/skills/review-pr/references/modules/input-output-modality.md

@@ -1,23 +0,0 @@
-# Input, Output, and Modality Contracts
-
-Primary design: [Input, Output, and Modality Contracts](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/input_output_modality_contracts/).
-
-Use for requests, prompt and modality types, message schemas, serialization,
-output types, accumulation, completion, and compatibility shims crossing
-entrypoint, orchestration, stage, connector, or model boundaries.
-
-## Contract checks
-
-- Give every boundary value an explicit modality and validated typed schema.
-- Preserve request and stage identity across conversion, serialization,
-  streaming updates, batching, cancellation, and errors.
-- Distinguish partial, final, empty, and failed output states for every modality.
-- Verify producer and consumer agreement on shape, layout, dtype, device,
-  ownership, metadata, ordering, and optional or unknown fields.
-- Keep internal objects out of public protocols; translate them at the owning
-  entrypoint.
-- Preserve wire compatibility deliberately and give deprecated shims a bounded
-  migration path.
-
-Require construction, round-trip, accumulation, completion, rejection, and
-compatibility tests at each changed producer-consumer boundary.

.claude/skills/review-pr/references/modules/model-integration.md

@@ -1,25 +0,0 @@
-# Model Integration
-
-Primary design: [Model Integration](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/model_integration/).
-
-Use for model registration, configuration adapters, preprocessing, checkpoint
-loading, stage inputs, model-specific hooks, shared layers, runners, and model
-execution. Use the diffusion family reference for diffusion models.
-
-## Contract checks
-
-- Declare explicitly how the model class, loader, input processor, stage
-  configuration, and runtime capabilities are selected.
-- Preserve weight-name mapping, dtype/device placement, optional-dependency
-  errors, and checkpoint-specific loading semantics.
-- Trace each typed input and output through preprocessing, runner state, model
-  call, and its actual consumer.
-- Reuse upstream vLLM behavior when sufficient; document and test the precise
-  difference for every override or patch.
-- Keep model code out of admission, cross-stage routing, public policy, and
-  terminal lifecycle ownership.
-- Place reusable behavior in shared modules and test it with more than one
-  integration.
-
-Require focused registry, loader, processor, runner, and representative model
-execution tests. Apply the model-addition check for new or expanded support.

.claude/skills/review-pr/references/modules/observability.md

@@ -1,21 +0,0 @@
-# Observability
-
-Primary design: [Observability](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/observability/).
-
-Use for metrics, logs, correlation fields, and cross-stage request visibility.
-
-## Contract checks
-
-- Preserve stable request and stage identity across entrypoints, orchestration,
-  stages, workers, errors, and terminal cleanup.
-- Treat metric names, units, labels, aggregation, and lifecycle as public
-  contracts; document any semantic change.
-- Keep labels bounded: never use request IDs, prompts, outputs, paths, or other
-  unbounded user values.
-- Register and reset metrics exactly once across repeated startup and shutdown,
-  and keep disabled instrumentation inexpensive.
-- Align emitted values with their actual timing and lifecycle owner rather than
-  reconstructing them from ambiguous client strings.
-
-Test registration, label sets, units, resets, error classification, and
-representative multi-stage emission.

.claude/skills/review-pr/references/modules/omni-connector.md

@@ -1,24 +0,0 @@
-# OmniConnector
-
-Primary design: [OmniConnector](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/omni_connector/).
-
-Use for connector contracts and model-agnostic data transfer across stages,
-processes, devices, or nodes. Connector implementations transport and
-synchronize data; they do not choose the next stage or implement model policy.
-
-## Contract checks
-
-- Prove producer and consumer agreement on request/stage identity, shape,
-  layout, dtype, placement, ownership, ordering, and completion.
-- Keep backend selection and metadata/key construction explicit; do not silently
-  reinterpret or drop payloads across SHM, store, network, or vendor paths.
-- Bound connect, put/get, retry, synchronization, and readiness waits with
-  backpressure, cancellation, and actionable errors.
-- Prevent route, endpoint, port, key, and buffer collisions across repeated
-  startup, concurrent requests, and replica replacement.
-- Release connections, handles, buffers, listener work, and stale sender state
-  on success, cancellation, failure, and shutdown.
-
-Load the matching communication feature design for a concrete backend. Require
-focused producer-consumer tests and the smallest runnable multi-process or
-multi-node path.

.claude/skills/review-pr/references/modules/profiling.md

@@ -1,21 +0,0 @@
-# Profiling
-
-Primary design: [Profiling](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/profiling/).
-
-Use for opt-in instrumentation and trace collection across supported profiler
-backends.
-
-## Contract checks
-
-- Keep expensive collection disabled by default and bounded by explicit start,
-  stop, timeout, and cleanup behavior.
-- Preserve scheduling, generated outputs, resource ownership, and concurrency
-  semantics apart from documented synchronization overhead.
-- Include stage, rank, worker, operation, and request correlation where useful
-  without embedding user payloads or secrets.
-- Make repeated start/stop and partial failure safe, including multi-rank trace
-  naming and artifact ownership.
-- Measure disabled and enabled overhead before making performance claims.
-
-Test the disabled path, repeated lifecycle, failure cleanup, trace context, and
-each affected backend.

.claude/skills/review-pr/references/modules/quantization.md

@@ -1,22 +0,0 @@
-# Quantization
-
-Primary design: [Quantization](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/quantization/).
-
-Use for method registration, checkpoint interpretation, layer replacement,
-reduced precision, platform capability, and runtime constraints.
-
-## Contract checks
-
-- Validate checkpoint metadata, selected method, supported layers, device
-  capability, required dependencies, and parallel layout before loading.
-- Preserve loader and weight-name mapping semantics, dtype, scale/granularity,
-  zero point, padding, and buffer handling through the real kernel consumer.
-- Fail clearly for unsupported combinations; do not silently choose a different
-  method or precision.
-- Keep online and pre-quantized checkpoint paths explicit and ensure patches or
-  fallbacks do not bypass model-owned loaders.
-- Require numerical comparison against a defined reference with explicit
-  tolerance before treating performance results as valid.
-
-Test registration, loading, representative layers, metadata, platform guards,
-parallel combinations, and numerical correctness separately from performance.

.claude/skills/review-pr/references/modules/stage-runtime.md

@@ -1,23 +0,0 @@
-# Stage Runtime and Replica Lifecycle
-
-Primary design: [Stage Runtime and Replica Lifecycle](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/module/stage_runtime/).
-
-Use for local or distributed placement, startup, readiness, stage pools,
-replica identity and membership, selection, affinity, liveness, draining, and
-stage-client or process lifecycle. Cross-stage request policy belongs to engine
-orchestration; model scheduling belongs to the owning runtime.
-
-## Contract checks
-
-- Acquire, replace, and retire replicas through one stage-runtime lifecycle.
-- Preserve stable replica identity and request affinity until termination or a
-  declared replica loss.
-- Make readiness explicit before admission; surface partial-startup and
-  membership failures without leaving half-initialized capacity.
-- Keep local and distributed semantics aligned for supported modes.
-- Make drain, shutdown, and cleanup idempotent across repeated signals and
-  process failure.
-
-Test startup, readiness, selection, affinity, membership changes, abort,
-process loss, draining, and repeated shutdown on affected local/distributed
-paths.

.claude/skills/review-pr/references/process/design-contracts.md

@@ -1,34 +0,0 @@
-# Resolve Design Contracts
-
-Use after freezing the review head and before selecting module or feature
-references. The maintained [design index](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/)
-defines two routing axes:
-
-- **Module designs** own code boundaries and invariants. Select one primary
-  module and a second only when the live producer-consumer path crosses it.
-- **Feature designs** describe behavior spanning modules. Load every feature
-  page whose implementation, default, support, or contract changes.
-
-## Resolution order
-
-1. Open `docs/design/index.md` in the reviewed head, not the reviewer's checkout
-   or published latest tree.
-2. Match changed behavior against each module page's `primary_code_paths`,
-   `primary_path_exceptions`, ownership boundary, and `depends_on` metadata.
-3. Read `status`, `architecture_state`, `last_verified_commit`, and any linked
-   in-flight work before treating prose as current behavior.
-4. Use current code and tests when a page is draft, deferred, stale, absent, or
-   conflicts with the frozen implementation. Report material documentation
-   drift separately.
-5. Treat candidate invariants and promotion gates as review questions until
-   repository policy, current code/tests, or owner-approved normative text
-   makes them enforceable. Do not turn a draft identifier into an automatic
-   blocker.
-6. Use published latest docs only for discovery when the reviewed head lacks a
-   page; never import a newer contract into an older branch silently.
-
-When behavior changes an active module or feature contract, require the same PR
-to update that page. Require a new page only when repository policy, an accepted
-RFC/issue, or explicit maintainer acceptance criteria do so; otherwise treat it
-as a non-blocking design suggestion. Do not demand a second page when an existing
-design already owns the exact contract.

.claude/skills/review-pr/references/process/general-checks.md

@@ -1,129 +0,0 @@
-# General Review Checks
-
-Apply these checks to every PR after freezing the review surface. A pattern is
-not a finding until the diff introduces or exposes a reachable trigger, impact,
-and smallest safe fix. Do not report unrelated backlog.
-
-Official docs: [contributing guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/)
-[feature compatibility](https://docs.vllm.ai/projects/vllm-omni/en/latest/user_guide/feature_compatibility/),
-and [design documents](https://docs.vllm.ai/projects/vllm-omni/en/latest/design/).
-
-## Contract and scope
-
-- Match the title/body claims to every changed production path, test, config,
-  dependency, generated artifact, and user-visible document.
-- Trace each changed value through public ingress, validation/defaulting,
-  producer, transformations, process or device boundaries, final consumer, and
-  terminal cleanup.
-- Check every applicable sync/async, offline/online, streaming/non-streaming,
-  feature-off, topology, and compatibility path without demanding unsupported
-  modes merely for symmetry.
-
-## Module, API, and class design
-
-Apply these rules to new or materially changed production code; do not require
-unrelated cleanup from untouched files.
-
-1. Start each source module with a concise module docstring that defines its
-   responsibility and boundaries and identifies its primary classes and key
-   functions. Place it after any required license header and before imports.
-2. Give every added or materially changed class and function a clear docstring
-   covering its responsibility, parameters, return value, raised exceptions,
-   and non-obvious invariants. Use explicit typed parameters at owned API
-   boundaries; avoid opaque `**kwargs` and `Any`. Allow them only when an
-   upstream or compatibility interface requires them, and document and validate
-   the accepted keys and concrete types.
-3. Move stable helpers shared by multiple features into an appropriately scoped
-   utility module. Do not let feature modules accumulate large collections of
-   unrelated private utility functions; keep a private helper local only when
-   it is single-purpose and tightly coupled to that feature.
-4. Keep every method on a key class within that class's stated responsibility,
-   and document non-obvious design decisions and invariants. Before adding a
-   method, prefer reuse, consolidation, or extension of an existing abstraction;
-   split the class when new behavior creates a separate responsibility or makes
-   the class unnecessarily long.
-5. Require changes to user-facing behavior to update `docs/`. When an existing
-   active module or feature design page owns the changed contract, update that
-   page. Require a new design page only when the reviewed branch's repository
-   policy, an accepted RFC/issue, or explicit maintainer acceptance criteria do
-   so; otherwise suggest it as non-blocking. For a major architectural change,
-   apply the branch's contributing policy for a design RFC or issue; the current
-   policy uses more than 500 changed production-code lines, excluding kernel,
-   data, config, and test changes. Resolve page status and authority through
-   [design-contracts.md](design-contracts.md), and do not demand a duplicate page
-   when an existing design owns the exact contract. When required, cover scope,
-   data flow, public contracts, failure behavior, alternatives, validation,
-   limitations, and rollout.
-6. Require every performance PR to provide reproducible base-versus-head A/B
-   results under the same hardware, software, model, workload, precision,
-   topology, warmup, repetitions, and measurement scope. Include exact commands,
-   variability, and a correctness or quality guard; one-sided or non-comparable
-   numbers are incomplete evidence. For a new model absent from the frozen base,
-   compare head with its pinned canonical reference implementation under rule 12
-   instead. Follow
-   [perf-verification.md](../checks/perf-verification.md) for the full protocol.
-7. Require every addition, removal, default change, or semantic change to a
-   user-facing inference API or CLI to explain why it is necessary, which
-   alternatives were considered, and why the chosen interface is preferable.
-   Record compatibility, deprecation or migration behavior, and the rationale
-   in the PR. Update the corresponding module and feature design documents when
-   they define the changed interface or workflow, or when policy requires one.
-8. Require every bug-fix PR to add an automated regression test that reproduces
-   the defect on the frozen base and passes on the fixed head. Exercise the
-   production path or nearest stable boundary and assert the corrected behavior,
-   not only process survival. Record the exact base/head command and result, and
-   place hardware- or model-specific coverage in the correct CI lane. A manual
-   reproduction supplements but does not replace the regression test.
-9. Require every new or materially changed recipe to follow
-   [`recipes/TEMPLATE.md`](../../../../../recipes/TEMPLATE.md) and the naming and
-   layout conventions in
-   [`recipes/README.md`](../../../../../recipes/README.md).
-   Complete every applicable summary, use-case, reference, hardware,
-   environment, exact-command, verification, and notes section with tested,
-   reproducible details; explain any intentional deviation in the PR.
-10. Require every new model to verify its supported modalities, platforms,
-    execution modes, and features with production-path evidence. Update
-    `docs/models/supported_models.md` and every applicable feature support or
-    compatibility table; do not claim support that the PR does not validate.
-    Follow
-    [model-addition-checklist.md](../checks/model-addition-checklist.md) for the
-    model-specific documentation checks.
-11. Require every new model PR to add or update its in-repository model-family
-    recipe under `recipes/` and its `recipes/README.md` index entry. Apply rule
-    9, and keep the recipe's model identifiers, tasks, serving modes, hardware,
-    commands, supported features, and limitations aligned with validated PR
-    evidence. An external recipe link does not replace the in-repository recipe.
-12. Require every new model to compare accuracy or output quality and performance
-    against a pinned baseline or canonical reference implementation. Match the
-    checkpoint, inputs, precision, hardware, workload, and measurement method;
-    provide exact commands, results, and explanations for material differences.
-    Prefer a detailed timing split for each stage and explain when it is
-    unavailable. Follow
-    [model-addition-checklist.md](../checks/model-addition-checklist.md) and
-    [perf-verification.md](../checks/perf-verification.md) for the evidence
-    contract.
-
-## Blocking risk scan
-
-| Risk | Prove before reporting |
-| --- | --- |
-| Correctness | A live input reaches a wrong output, exception, silent drop, shape/dtype/device mismatch, or partially initialized state. |
-| Compatibility | A supported API, config key, default, serialization schema, model identifier, or caller breaks without validation, migration, or deprecation. |
-| Lifecycle | Allocation or startup lacks cleanup on partial failure, timeout, cancellation, shutdown, or repeated requests. |
-| Concurrency/distribution | Ordering, identity, rank, world size, completion, timeout, backpressure, or collective assumptions fail on a supported path. |
-| Cache/shared state | Identity omits a correctness-affecting input, or isolation, invalidation, disabled behavior, eviction, or cleanup is incomplete. |
-| Async behavior | Blocking I/O, sleep, a lock across `await`, or unnecessary serialization harms a reachable async path. |
-| Security/data handling | Secrets, user payloads, unsafe deserialization/eval/shell, unvalidated paths, or unbounded metric labels are reachable. |
-| Validation evidence | Tests bypass the production dispatcher, mock away the change, use unrealistic types/MRO, or cannot fail when the defect returns. |
-| User contract | User-visible model, feature, API, CLI, config, default, or compatibility behavior changes without accurate docs or examples. |
-
-Search bounded callers and sibling implementations before reporting dead code,
-duplication, or a missed consumer. Keep new abstractions only when they have a
-distinct live caller, invariant, or compatibility need.
-
-## Finding bar
-
-Anchor each finding to a changed `path:line`; name the trigger or call path,
-current behavior, impact, and smallest fix direction. Treat pending CI, missing
-hardware, or unsupported measurements as validation gaps unless the repository
-contract makes that evidence a merge requirement.

.claude/skills/review-pr/references/process/review-execution.md

@@ -1,191 +0,0 @@
-# Review Execution and Delivery
-
-Use this reference for every review. It defines snapshot collection, gates,
-validation records, delivery permissions, maintainer tone, and re-review.
-
-Official docs: [contributing guide](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/)
-and [CI failure triage](https://docs.vllm.ai/projects/vllm-omni/en/latest/contributing/ci/failures/).
-
-## Contents
-
-- [Freeze the review surface](#freeze-the-review-surface)
-- [Report status before analysis](#report-status-before-analysis)
-- [Apply review gates](#apply-review-gates)
-- [Run bounded validation](#run-bounded-validation)
-- [Deliver maintainer-style findings](#deliver-maintainer-style-findings)
-- [Re-review safely](#re-review-safely)
-
-## Freeze the review surface
-
-For a GitHub PR, read the base/head SHA before and after fetching metadata and
-the diff:
-
-```bash
-gh api "repos/vllm-project/vllm-omni/pulls/<PR>" \
-  --jq '{base_sha: .base.sha, head_sha: .head.sha}'
-REVIEW_FIELDS="number,url,title,body,isDraft,baseRefName,headRefName,mergeable,mergeStateStatus,statusCheckRollup,files"
-gh pr view <PR> --repo vllm-project/vllm-omni \
-  --json "${REVIEW_FIELDS}"
-gh pr diff <PR> --repo vllm-project/vllm-omni
-gh api "repos/vllm-project/vllm-omni/pulls/<PR>" \
-  --jq '{base_sha: .base.sha, head_sha: .head.sha}'
-```
-
-Discard the snapshot if either SHA changed. Do not mix comments or validation
-from different heads.
-
-After the SHAs stabilize, fetch and materialize a trusted `head_sha` in an
-isolated detached worktree. Run every source read, `rg` search, import, and test
-from that snapshot, not the caller's checkout. A detached worktree provides
-snapshot isolation, not a security boundary.
-
-Treat a fork head as untrusted unless the user and environment policy explicitly
-establish trust. Never run its imports, tests, builds, hooks, package setup, or
-repo-configurable linters/plugins on the reviewer host. Execute them only in a
-disposable sandbox or VM with no credentials or inherited secrets, no host agent
-or service sockets, minimal read-only host mounts, disabled or explicitly
-allowlisted network, resource/time limits, and destruction after the run. If
-that boundary is unavailable, limit the review to the remote diff, SHA-addressed
-reads such as `git show <head_sha>:<path>`, and existing CI evidence; report all
-executable validation as a gap.
-
-Before the first source read, record a pristine snapshot fingerprint outside
-the reviewed worktree. Include `HEAD`, the NUL-delimited index entries and blob
-IDs, and a NUL-safe manifest of every worktree entry except Git metadata,
-including tracked, untracked, and ignored paths with file type, mode, symlink
-target, and content hash. Before each validation group and delivery, recompute
-and byte-compare the fingerprint as well as asserting `HEAD == head_sha`. If a
-tool changes or creates any entry, discard affected evidence and recreate the
-snapshot before another group; do not rely on `HEAD` alone or clean an unknown
-worktree in place. If an exact snapshot cannot be created, use SHA-addressed
-reads and report filesystem-dependent validation as a gap.
-
-For a local branch/worktree, determine the target ref from the user, current PR,
-or configured upstream; never infer it from the branch name. Resolve the target
-once and include all task-owned worktree state:
-
-```bash
-git status --porcelain=v2 -z
-git rev-parse HEAD
-git rev-parse <target-ref>
-git merge-base <target-base-sha> HEAD
-git diff --stat <comparison-commit>
-git diff --name-status <comparison-commit>
-git diff --binary <comparison-commit>
-git diff --cached --binary <comparison-commit>
-git diff --binary
-git ls-files --others --exclude-standard -z
-```
-
-Freeze the exact bytes of every in-scope untracked file from the NUL-delimited
-list, plus a NUL-safe path, file-type, mode, and content-hash manifest. Also
-fingerprint `HEAD`, the target and merge base, porcelain status, and both binary
-index and worktree patches. Recording only untracked names is insufficient.
-Keep these snapshots in the evidence packet and do not mutate the reviewed
-checkout during a read-only review.
-
-For local changes without PR metadata, mark the title/body as synthetic. Base
-them on the user request and commit messages without inventing validation claims.
-
-If no PR, branch, or usable worktree is identifiable, ask for a PR URL/number or
-explicit base and head rather than guessing.
-
-## Report status before analysis
-
-Within 60 seconds of starting, and before source searches or tests, send this
-host update:
-
-```text
-Pinned head: <SHA>
-Base/comparison: <ref and SHA>
-CI: <pass/fail/pending/not applicable>
-Mergeability: <state/not applicable>
-Preliminary findings: <brief finding or none yet>
-```
-
-Mark early findings as preliminary and continue. This is not a GitHub comment.
-
-## Apply review gates
-
-- Report draft/WIP state. Continue a local review when explicitly requested,
-  but do not publish review events without separate authorization.
-- Record DCO, pre-commit, required CI, and mergeability. Pending or unknown gates
-  do not block source review.
-- Treat a failed gate as its own evidence. Do not restate its formatting/lint
-  output as a new code-review finding.
-- Open CI logs only when the first failing step overlaps the frozen diff or
-  blocks the verdict. Start with the first error, not the last cascade.
-- Treat the PR body as navigation. Commands, benchmark tables, and claimed tests
-  become evidence only after their provenance and relevance are checked.
-
-## Run bounded validation
-
-Keep one evidence packet for files read, bounded searches, callers, tests, CI,
-hardware, routes, and findings. Reuse it rather than refetching facts.
-
-Before pytest, run a short import/version compatibility check. Record each
-validation result with:
-
-```text
-repo, head SHA, command, result, Python/platform, dependency or lock fingerprint
-```
-
-After preflight, run targeted tests and low-cost static checks alongside source
-inspection when possible. Imports, tests, builds, and linters may create caches
-or rewrite files, so isolate each potentially mutating group in a disposable
-snapshot or recreate the pinned snapshot before continuing. Map source symbols
-to tests with bounded `rg` searches rather than assuming the test directory
-mirrors production paths.
-
-Classify failures as code, test, infrastructure, or flaky before reporting.
-Skipped hardware tests are gaps, not passes. For available hardware, verify the
-smallest representative unit/E2E path and compare actual output with PR claims.
-
-## Deliver maintainer-style findings
-
-Default to roughly 1-5 short comments, but treat that as calibration rather than
-a quota: report every real blocker and report no finding when there is no issue.
-
-Write each finding as:
-
-```text
-[P1] Short imperative title — path/to/file.py:<line>
-<Trigger or call path>. <Current behavior and impact>. <Smallest fix direction>.
-```
-
-Use [maintainer-style-study.md](../delivery/maintainer-style-study.md) for
-comment tone.
-Keep rule IDs, grades, and audit matrices internal unless the user asks for the
-complete audit.
-
-Verify every inline `path:line` against the frozen diff before delivery. For a
-PR, re-read the remote head and byte-compare the detached snapshot fingerprint,
-or recreate it from `head_sha`, before asserting current lines. For a local
-review, recompute and byte-compare the frozen `HEAD`, target, merge base, status,
-index patch, worktree patch, and untracked-content manifest. Any mismatch makes
-the review stale; discard the affected evidence and restart. Prefer one
-root-cause comment to several symptom comments.
-
-Local presentation is the default. Only explicit authorization permits GitHub
-posting. When authorized, publish one consolidated final review after
-validation; do not post preliminary or incremental comments. Submit a review
-event (`APPROVE`, `COMMENT`, or `REQUEST_CHANGES`) only when the user explicitly
-chooses that event.
-
-Reviewer requests and owner `@mention` comments are separate external writes;
-follow [review-requests.md](../delivery/review-requests.md) when the user asks
-for them.
-
-## Re-review safely
-
-Freeze the new head and compare it with the previously reviewed SHA. Then:
-
-1. inspect the delta and every file affected by conflict resolution or rebase;
-2. revalidate earlier findings against current lines and behavior;
-3. read unresolved, non-outdated threads and the author's evidence;
-4. rerun only checks invalidated by the delta;
-5. look for new regressions introduced by the fix;
-6. do not repeat resolved or outdated comments.
-
-If the target head changes during re-review, discard stale validation and start
-again from the new snapshot.

.claude/skills/review-pr/references/process/review-routing.md

@@ -1,76 +0,0 @@
-# Module and Feature Review Routing
-
-Read [design-contracts.md](design-contracts.md) first. Route from the frozen
-head's live producer-consumer behavior, then confirm the result against its
-`docs/design/` metadata. Titles and paths are evidence, not the deciding rule.
-
-## Primary module contract
-
-Choose one primary module and a second only when the live call path crosses a
-documented dependency or primary-path exception.
-
-| Module | Live behavior signals | Read |
-| --- | --- | --- |
-| Entrypoints | Offline/CLI/API ingress, validation, rendering, streaming, sessions | [entrypoints.md](../modules/entrypoints.md) |
-| Configuration | Schema, defaults, deploy/stage construction, registry, topology | [configuration.md](../modules/configuration.md) |
-| I/O and Modality | Requests, messages, serialization, output types, accumulation, completion | [input-output-modality.md](../modules/input-output-modality.md) |
-| Error Contracts | Classification, fatality, propagation, sanitization, public rendering | [error-contracts.md](../modules/error-contracts.md) |
-| Engine Orchestration | Cross-stage routing, request state, ordering, RPC correlation, terminal convergence | [engine-orchestration.md](../modules/engine-orchestration.md) |
-| Stage Runtime | Placement, startup, readiness, replicas, affinity, membership, shutdown | [stage-runtime.md](../modules/stage-runtime.md) |
-| OmniConnector | Cross-stage/process/device/node transport and synchronization | [omni-connector.md](../modules/omni-connector.md) |
-| Model Integration | Registration, preprocessing, loading, runners, model-specific execution | [model-integration.md](../modules/model-integration.md) |
-| AR Runtime | Scheduling, request/cache state, adapters, workers, upstream vLLM semantics | [ar-runtime.md](../modules/ar-runtime.md) |
-| Diffusion Family | Diffusion runtime, models, batching, parallelism, or offload | [diffusion.md](../modules/diffusion.md) |
-| Execution Platforms | Hardware selection, capabilities, vendor workers, kernels, patches | [execution-platforms.md](../modules/execution-platforms.md) |
-| Cache Management | Cache identity, validity, reuse, eviction, reset, teardown | [cache-management.md](../modules/cache-management.md) |
-| Quantization | Method/metadata selection, layer mapping, reduced precision, constraints | [quantization.md](../modules/quantization.md) |
-| Observability | Metrics, logs, labels, units, correlation, lifecycle | [observability.md](../modules/observability.md) |
-| Profiling | Opt-in instrumentation, traces, start/stop lifecycle, overhead | [profiling.md](../modules/profiling.md) |
-| Benchmarking | Workloads, metric computation, benchmark CLI, result metadata | [benchmarking.md](../modules/benchmarking.md) |
-
-For tests-, docs-, CI-, or recipe-only changes, route to the production module
-whose contract they protect. When none exists, use the applicable evidence
-check without inventing a production owner.
-
-## Feature-design overlays
-
-Load every category whose documented behavior, enablement, default, support, or
-compatibility changes.
-
-| Feature-design section | Read |
-| --- | --- |
-| Runtime and stage execution | [runtime-stage-execution.md](../features/runtime-stage-execution.md) |
-| Communication and concrete connectors | [communication.md](../features/communication.md) |
-| Diffusion acceleration | [diffusion-acceleration.md](../features/diffusion-acceleration.md) |
-| Infrastructure and performance | [infrastructure-performance.md](../features/infrastructure-performance.md) |
-
-## Evidence and change overlays
-
-| Signal | Read | Optional repo-local skill |
-| --- | --- | --- |
-| New or expanded model, loader, processor, registry, or stage config | [model-addition-checklist.md](../checks/model-addition-checklist.md) | [`add-tts-model`](../../../add-tts-model/SKILL.md) or [`add-diffusion-model`](../../../add-diffusion-model/SKILL.md) |
-| Latency, throughput, memory, scaling, precision, or quality claim | [perf-verification.md](../checks/perf-verification.md) | [`diffusion-perf-opt`](../../../diffusion-perf-opt/SKILL.md) for diffusion |
-| Tests changed, absent for risky behavior, or test-only | [test-quality-evaluation.md](../checks/test-quality-evaluation.md) | [`vllm-omni-test`](../../../vllm-omni-test/SKILL.md) |
-| CI, examples, docs, public behavior, or contributor evidence | [tests-docs-checklist.md](../checks/tests-docs-checklist.md) | None |
-| Suitable hardware/server and runnable affected path | [verification.md](../checks/verification.md) | None |
-| User asks who should review or requests owner notification | [review-requests.md](../delivery/review-requests.md) | None |
-
-Use [`quantization`](../../../quantization/SKILL.md) for a quantization module
-change and [`$vllm-omni-npu-model-runner-upgrade`](../../../vllm-omni-npu-upgrade/SKILL.md)
-for an NPU execution-platform change when those skills are available.
-
-For a bug fix, require a reachable reproduction and regression test. For a
-refactor, prove parity and remove obsolete paths. For a feature, verify the
-public/config contract, module integration, compatibility/default behavior,
-production dispatch, feature design, and docs.
-
-## Calibrate findings
-
-- **P0:** security exposure, data corruption, or broad project unusability.
-- **P1:** reachable runtime failure, wrong output, compatibility break, or
-  unsafe lifecycle in the changed behavior.
-- **P2:** real non-blocking defect with a concrete future failure mode.
-
-Treat draft candidate invariants, missing hardware, and unsupported claims as
-questions or validation gaps unless current code, tests, or policy makes them a
-merge requirement.