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

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 · Model Executor Test · Shard %N/%t"
      agent_pool: mi300_1
      parallelism: 3
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      timeout_in_minutes: 90
      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
        - "pytest -sv tests/model_executor -m 'core_model and cpu and not omni' --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB"

    - label: "Simple · Omni Processor Test"
      agent_pool: mi300_1
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      timeout_in_minutes: 60
      commands:
        - export VLLM_ROCM_USE_AITER=0
        - "pytest -sv tests/model_executor/models/test_omni_processing.py -m 'core_model and cpu and omni'"

    - label: "Simple · Diffusion Test · Shard %N/%t"
      agent_pool: mi300_1
      parallelism: 4
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      timeout_in_minutes: 45
      # Buildkite's status-based rule cannot prove every exit 134 is a GPU hang.
      # It retries 134 once; the Kubernetes job retry starts a fresh pod.
      # Assertions (1), timeouts (124), and OOMs (137) remain non-retryable.
      retry:
        automatic:
          - exit_status: 134
            limit: 1
      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
        # Keep multi-GPU tests out of this one-GPU pool even when their module
        # also carries the cpu marker for unit tests.
        # Keep π0.5 CPU units out of these shards: CUDA READY/MERGE already run
        # the same suite mandatorily, and AMD covers it non-blocking in nightly.
        - "pytest -sv tests/diffusion -m 'core_model and cpu and not (cards_2 or cards_3 or cards_4 or cards_5 or cards_6 or cards_7 or cards_8)' --ignore=tests/diffusion/cache/test_teacache_extractors.py --ignore=tests/diffusion/models/pi05/test_pi05_units.py --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB"

    - label: "Diffusion · AuK VAE GPU Test"
      agent_pool: mi300_1
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      timeout_in_minutes: 40
      commands:
        - export VLLM_ROCM_USE_AITER=0
        - >-
          timeout --signal=TERM --kill-after=2m 35m
          pytest -sv tests/diffusion/models/auk/test_auk_vae_fastpath.py
          -m 'core_model and rocm and cards_1' --run-level core_model

    - label: "Simple · Engine&Entrypoints Test"
      agent_pool: mi300_1
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      commands:
        - export VLLM_ROCM_USE_AITER=0
        - "pytest -sv tests/entrypoints tests/engine -m 'core_model and cpu'"

    - label: "Simple · Other Test"
      agent_pool: mi300_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
        - "pytest -sv tests/ -m 'core_model and cpu' --ignore=tests/diffusion --ignore=tests/model_executor --ignore=tests/entrypoints --ignore=tests/engine  --ignore=tests/diffusion/cache/test_teacache_extractors.py"

- group: ":card_index_dividers: Diffusion Test"
  steps:
    # AR paged attention is real GPU work, including cold AITER compilation.
    # Keep its complete numerical matrix out of the CPU-marked Simple shards.
    - label: "ROCm · AR Diffusion Paged Attention GPU Test"
      agent_pool: mi300_1
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      timeout_in_minutes: 20
      commands:
        - export VLLM_ROCM_USE_AITER=1
        - export VLLM_OMNI_AR_FA_REQUIRED=1
        - export AITER_JIT_DIR="/tmp/vllm-omni-ar-aiter-$$BUILDKITE_JOB_ID"
        - export TORCH_EXTENSIONS_DIR="/tmp/vllm-omni-ar-torch-extensions-$$BUILDKITE_JOB_ID"
        - mkdir -p "$$AITER_JIT_DIR" "$$TORCH_EXTENSIONS_DIR"
        - >-
          timeout --signal=TERM --kill-after=2m 15m
          pytest -sv tests/diffusion/ar_diffusion/test_paged_attention.py
          -m 'core_model and rocm and MI325 and cards_1' --run-level core_model

    - label: "Diffusion · LoRA Test"
      agent_pool: mi300_1
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      artifact_paths:
        - lora-server.log
      commands:
        - pytest -sv tests/diffusion/lora/ -m 'advanced_model and cuda' --run-level "advanced_model" 2>&1 | tee lora-server.log

    - label: "Diffusion Model CPU offloading Test"
      agent_pool: mi300_1
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      commands:
        - export VLLM_LOGGING_LEVEL=DEBUG
        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
        - export DIFFUSION_ATTENTION_BACKEND=TORCH_SDPA
        - pytest -s -v tests/diffusion/offloader/test_diffusion_cpu_offload.py
        - >-
          pytest -s -v tests/diffusion/offloader/test_diffusion_layerwise_offload.py
          --deselect='tests/diffusion/offloader/test_diffusion_layerwise_offload.py::test_layerwise_offload_diffusion_model[stabilityai/stable-audio-open-1.0]'

    # TODO: Diagnose unstable Stable Audio layerwise-offload memory savings on ROCm.
    - label: "Diffusion Stable Audio Layerwise Offload Test (quarantined)"
      agent_pool: mi300_1
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: NonBlocking
      commands:
        - export VLLM_LOGGING_LEVEL=DEBUG
        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
        - >-
          pytest -s -v
          'tests/diffusion/offloader/test_diffusion_layerwise_offload.py::test_layerwise_offload_diffusion_model[stabilityai/stable-audio-open-1.0]'

    - label: "Diffusion Sequence Parallelism Test (Need 4 GPUs) · Shard 1/2"
      agent_pool: mi300_4
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      timeout_in_minutes: 40
      grade: Blocking
      commands:
        - export VLLM_LOGGING_LEVEL=DEBUG
        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
        - pytest -s -v tests/diffusion/distributed/test_sequence_parallel.py

    - label: "Diffusion Sequence Parallelism Test (Need 4 GPUs) · Shard 2/2"
      agent_pool: mi300_4
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      timeout_in_minutes: 40
      grade: Blocking
      commands:
        - export VLLM_LOGGING_LEVEL=DEBUG
        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
        - pytest -s -v tests/diffusion/distributed/test_ulysses_uaa_perf.py

    # merge-only tests
    - label: "Diffusion Tensor Parallelism Test"
      agent_pool: mi300_2
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      commands:
        - pytest -s -v tests/diffusion/distributed/test_tensor_parallel.py
        - >-
          timeout 20m pytest -s -v
          tests/diffusion/attention/test_ulysses_uaa.py::test_ulysses_uaa_2d_mask_layout_matches_baseline
          -m 'core_model and cards_2'
          --run-level "core_model"

    - label: "Diffusion Model Test"
      agent_pool: mi300_1
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      commands:
        # A cold Z-Image run spends about six minutes loading weights before
        # the first-request AITER compilation, which can itself exceed 23m.
        - timeout 55m pytest -s -v tests/e2e/offline_inference/test_z_image.py

    - label: "Diffusion GPU Worker Test"
      agent_pool: mi300_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: mi300_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: mi300_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: mi300_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: mi300_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: mi300_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/offline_inference/test_qwen3_omni_colocate_async.py -m 'advanced_model and cuda' --run-level 'advanced_model'

    - label: "Qwen3-TTS CustomVoice E2E Test · Shard %N/%t"
      agent_pool: mi300_1
      parallelism: 3
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      timeout_in_minutes: 80
      commands:
        - |
          timeout --signal=TERM --kill-after=2m 80m bash -c '
            export VLLM_LOGGING_LEVEL=DEBUG
            export VLLM_WORKER_MULTIPROC_METHOD=spawn
            export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
            TESTS=(
              "tests/e2e/online_serving/test_qwen3_tts_customvoice.py::test_default_cuda_graph_startup[async_chunk]"
              "tests/e2e/online_serving/test_qwen3_tts_customvoice.py::test_text_to_audio_002[async_chunk]"
              "tests/e2e/offline_inference/test_qwen3_tts_customvoice.py::test_text_to_audio_001[no_cuda_graph]"
            )
            TEST="$${TESTS[$$BUILDKITE_PARALLEL_JOB]}"
            pytest -s -v "$$TEST" -m "advanced_model" --run-level "advanced_model"
          '

    # TODO: Restore this case to the blocking sharded step once its long-running
    # Whisper validation on AMD CI is resolved.
    - label: "Qwen3-TTS CustomVoice async_chunk Test (quarantined)"
      agent_pool: mi300_1
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: NonBlocking
      timeout_in_minutes: 80
      commands:
        - |
          timeout --signal=TERM --kill-after=2m 75m 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::test_text_to_audio_001[async_chunk]" -m "advanced_model" --run-level "advanced_model"
          '

    - label: "Qwen3-TTS Base E2E Test"
      agent_pool: mi300_1
      depends_on: amd-build
      mirror_hardwares: [amdproduction]
      grade: Blocking
      timeout_in_minutes: 50
      commands:
        - export VLLM_LOGGING_LEVEL=DEBUG
        - export VLLM_WORKER_MULTIPROC_METHOD=spawn
        - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
        - timeout 40m 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: mi300_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: mi300_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: mi300_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"