[CI/Build] Diff-aware source_file_dependencies for CUDA/NPU pipelines (#6597)

Signed-off-by: wangyu <410167048@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>

.buildkite/common/ci_source_file_dependencies.yml

@@ -0,0 +1,438 @@
+# Uploader-only path-prefix presets for CUDA L2–L5 and NPU L4 test YAML.
+# Referenced as ``source_file_dependencies: omni_qwen3_omni_function`` (or a list of
+# keys) on a step; ``upload_pipeline.py`` expands the key(s) only.
+#
+# YAML anchors above the registry hold model business-code paths. Job keys
+# ({model}_function / _perf / _accuracy / _reliability / _doc / _cov) alias
+# those anchors and add the scripts the job actually runs. Feature keys below
+# are unchanged. ``source_filter_fallback`` is not a job key: when no job-key
+# prefix matches, a matching diff keeps every job for that upload.
+#
+# YAML anchors are nested lists; the loader flattens them.
+
+x-qwen3-tts: &qwen3_tts
+  - vllm_omni/worker/gpu_model_runner.py
+  - vllm_omni/model_executor/models/qwen3_tts/
+  - vllm_omni/model_executor/models/common/qwen3_code_predictor.py
+  - vllm_omni/model_executor/models/common/snake_activation.py
+  - vllm_omni/model_executor/models/common/alias_free_activation.py
+  - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
+  - vllm_omni/deploy/qwen3_tts.yaml
+  - vllm_omni/entrypoints/openai/serving_speech.py
+  - vllm_omni/entrypoints/openai/tts_adapters/
+  - vllm_omni/engine/stage_pool.py
+
+x-minicpmo-4-5: &minicpmo_4_5
+  - vllm_omni/model_executor/models/minicpmo_4_5/
+  - vllm_omni/model_executor/models/step_audio2/
+  - vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
+  - vllm_omni/model_executor/models/cosyvoice3/utils.py
+  - vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
+  - vllm_omni/deploy/minicpmo_4_5.yaml
+  - vllm_omni/transformers_utils/chat_templates/minicpmo45_native.jinja
+
+x-minicpmo-4-5-duplex: &minicpmo_4_5_duplex
+  - vllm_omni/deploy/minicpmo_4_5_duplex.yaml
+  - vllm_omni/engine/duplex/
+  - vllm_omni/entrypoints/duplex/
+  - vllm_omni/clients/
+  - vllm_omni/entrypoints/duplex_request_client.py
+  - vllm_omni/outputs/duplex.py
+  - vllm_omni/model_executor/duplex_sampling.py
+  - vllm_omni/experimental/fullduplex/
+  - 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/engine/orchestrator.py
+  - vllm_omni/entrypoints/cli/serve.py
+  - vllm_omni/entrypoints/openai/api_server.py
+  - vllm_omni/entrypoints/openai/duplex_capability.py
+  - vllm_omni/config/stage_config.py
+
+x-qwen2-5-omni: &qwen2_5_omni
+  - vllm_omni/model_executor/models/qwen2_5_omni/
+  - vllm_omni/model_executor/stage_input_processors/qwen2_5_omni.py
+  - vllm_omni/deploy/qwen2_5_omni.yaml
+
+x-qwen3-omni: &qwen3_omni
+  - vllm_omni/entrypoints/openai/serving_chat.py
+  - vllm_omni/model_executor/models/qwen3_omni/
+  - vllm_omni/model_executor/models/common/qwen3_code_predictor.py
+  - vllm_omni/model_executor/models/common/snake_activation.py
+  - vllm_omni/model_executor/models/qwen2_5_omni/qwen2_5_omni_thinker.py
+  - vllm_omni/model_executor/models/qwen3_tts/cuda_graph_decoder_wrapper.py
+  - vllm_omni/model_executor/stage_input_processors/qwen3_omni.py
+  - vllm_omni/deploy/qwen3_omni_moe.yaml
+  - vllm_omni/deploy/qwen3_omni_moe_thinking.yaml
+
+x-wan22: &wan22
+  - vllm_omni/diffusion/models/wan2_2/
+  - vllm_omni/diffusion/models/dmd2/
+
+x-cosmos3: &cosmos3
+  - vllm_omni/diffusion/models/cosmos3/
+  - vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_wan.py
+  - vllm_omni/experimental/world_models/
+  - vllm_omni/model_extras/cosmos3.py
+
+x-qwen-image: &qwen_image
+  - vllm_omni/diffusion/models/qwen_image/
+  - vllm_omni/diffusion/models/dmd2/
+  - vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_qwenimage.py
+
+x-hunyuan-image3: &hunyuan_image3
+  - vllm_omni/diffusion/models/hunyuan_image3/
+  - vllm_omni/model_executor/models/hunyuan_image3/
+  - vllm_omni/deploy/hunyuan_image3_dit.yaml
+
+x-minimax-h3: &minimax_h3
+  - vllm_omni/diffusion/models/minimax_h3/
+
+x-hunyuan-video: &hunyuan_video
+  - vllm_omni/diffusion/models/hunyuan_video/
+  - vllm_omni/model_executor/models/hunyuan_video/
+
+x-ltx2: &ltx2
+  - vllm_omni/diffusion/models/ltx2/
+  - vllm_omni/model_extras/ltx2.py
+
+x-sana-video: &sana_video
+  - vllm_omni/diffusion/models/sana_video/
+  - vllm_omni/model_extras/sana_video.py
+
+x-z-image: &z_image
+  - vllm_omni/diffusion/models/z_image/
+
+x-stable-audio: &stable_audio
+  - vllm_omni/diffusion/models/stable_audio/
+
+x-lingbot-video: &lingbot_video
+  - vllm_omni/diffusion/models/lingbot_video/
+  - vllm_omni/model_extras/lingbot_video.py
+
+x-lingbot-world: &lingbot_world
+  - vllm_omni/diffusion/models/lingbot_world/
+
+
+source_file_dependencies:
+  # Shared uploader/registry paths. Not a job key — do not attach this to a step.
+  # Used only when no job-key prefix matches: then a hit keeps every job.
+  source_filter_fallback:
+    - .buildkite/common/scripts/upload_pipeline.py
+    - .buildkite/common/ci_source_file_dependencies.yml
+    - .buildkite/common/ci_mirror_hardwares.yml
+    - tests/helpers/
+
+  # --- features ---
+  diffusion_distributed_attention:
+    - 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/
+
+  custom_pipeline:
+    - 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/
+
+  rlhf_verl_omni:
+    - 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/
+
+  # Tiny-model diffusion jobs (shared across many model trees under models/).
+  diffusion_tiny_model:
+    - tests/model_tests/diffusion/
+    - vllm_omni/diffusion/models/
+
+  diffusion_offloader:
+    - tests/diffusion/offloader/
+    - vllm_omni/diffusion/offloader/
+
+  diffusion_quantization:
+    - tests/diffusion/quantization/
+    - vllm_omni/diffusion/quantization/
+
+  # --- models ---
+  # --- omni / tts jobs ---
+  omni_qwen3_omni_function:
+    - *qwen3_omni
+    - tests/e2e/offline_inference/test_qwen3_omni.py
+    - tests/e2e/offline_inference/test_qwen3_omni_colocate_async.py
+    - tests/e2e/offline_inference/test_qwen3_omni_autoround_w4a16_expansion.py
+    - tests/e2e/offline_inference/test_qwen3_omni_modelopt_nvfp4_w4a4.py
+    - tests/e2e/online_serving/test_qwen3_omni.py
+    - tests/e2e/online_serving/test_qwen3_omni_expansion.py
+    - tests/e2e/online_serving/test_qwen3_omni_multi_replicas.py
+
+  omni_qwen3_omni_accuracy:
+    - *qwen3_omni
+    - tests/e2e/accuracy/qwen3_omni/
+
+  omni_qwen3_omni_perf:
+    - *qwen3_omni
+    - tests/dfx/perf/scripts/run_benchmark.py
+    - tests/dfx/perf/tests/test_qwen3_omni_vllm_text.json
+    - tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
+    - tests/dfx/perf/tests/test_qwen3_omni_no_async_chunk.json
+    - tests/dfx/perf/tests/test_qwen3_omni_multi_replicas.json
+
+  omni_qwen3_omni_reliability:
+    - *qwen3_omni
+    - tests/dfx/reliability/test_reliability_qwen3_omni.py
+
+  omni_qwen3_omni_doc:
+    - *qwen3_omni
+    - examples/online_serving/qwen3_omni/
+    - examples/online_serving/openai_chat_completion_client_for_multimodal_generation.py
+    - tests/examples/online_serving/test_qwen3_omni.py
+
+  omni_qwen2_5_omni_doc:
+    - *qwen2_5_omni
+    - examples/online_serving/qwen2_5_omni/
+    - examples/online_serving/openai_chat_completion_client_for_multimodal_generation.py
+    - tests/examples/online_serving/test_qwen2_5_omni.py
+
+  omni_minicpmo_4_5_function:
+    - *minicpmo_4_5
+    - 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
+
+  omni_minicpmo_4_5_accuracy:
+    - *minicpmo_4_5
+    - tests/e2e/accuracy/minicpmo_4_5/
+
+  omni_minicpmo_4_5_perf:
+    - *minicpmo_4_5
+    - tests/dfx/perf/scripts/run_benchmark.py
+    - tests/dfx/perf/tests/test_minicpmo_4_5_ready.json
+    - tests/dfx/perf/tests/test_minicpmo_4_5.json
+
+  omni_minicpmo_4_5_doc:
+    - *minicpmo_4_5
+    - examples/online_serving/minicpmo/realtime_web/
+    - examples/online_serving/minicpmo/realtime_duplex_demo.py
+    - tests/examples/test_minicpmo_realtime_web_server.py
+    - tests/examples/test_minicpmo_realtime_web_static.py
+    - tests/examples/test_minicpmo_realtime_duplex_simple_demo.py
+
+  omni_minicpmo_4_5_duplex_function:
+    - *minicpmo_4_5
+    - *minicpmo_4_5_duplex
+    - 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_duplex_client_live.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_server_vad.py
+    - tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py
+    - tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py
+    - tests/assets/minicpmo_4_5/
+    - tests/clients/
+    - tests/engine/duplex/
+    - tests/entrypoints/duplex/
+    - tests/model_executor/models/minicpmo_4_5/duplex/
+
+  omni_minicpmo_4_5_duplex_perf:
+    - *minicpmo_4_5
+    - *minicpmo_4_5_duplex
+    - tests/dfx/perf/scripts/run_benchmark.py
+    - tests/dfx/perf/tests/test_minicpmo_4_5_duplex_seed_tts.json
+
+  tts_qwen3_tts_function:
+    - *qwen3_tts
+    - tests/e2e/features/prefill_phase/
+    - tests/e2e/offline_inference/test_qwen3_tts_base.py
+    - tests/e2e/offline_inference/test_qwen3_tts_customvoice.py
+    - tests/e2e/online_serving/test_qwen3_tts_base.py
+    - tests/e2e/online_serving/test_qwen3_tts_base_expansion.py
+    - tests/e2e/online_serving/test_qwen3_tts_customvoice.py
+    - tests/e2e/online_serving/test_qwen3_tts_customvoice_expansion.py
+
+  tts_qwen3_tts_perf:
+    - *qwen3_tts
+    - tests/dfx/perf/scripts/run_benchmark.py
+    - tests/dfx/perf/tests/test_tts.json
+
+  tts_qwen3_tts_cov:
+    - *qwen3_tts
+    - .buildkite/common/scripts/run_cov_split.sh
+    - pyproject.toml
+    - tests/e2e/offline_inference/test_qwen3_tts_base.py
+    - tests/e2e/online_serving/test_qwen3_tts_base.py
+
+  # --- diffusion jobs ---
+  diffusion_wan22_function:
+    - *wan22
+    - tests/e2e/offline_inference/test_wan22_t2v.py
+    - tests/e2e/offline_inference/test_wan22_autoround_w4a16_expansion.py
+    - tests/e2e/online_serving/test_wan22_t2v.py
+    - tests/e2e/online_serving/test_wan22_expansion.py
+
+  diffusion_wan22_accuracy:
+    - *wan22
+    - tests/e2e/accuracy/wan22_i2v/
+    - tests/e2e/accuracy/test_diffusers_backend_similarity.py
+
+  diffusion_wan22_perf:
+    - *wan22
+    - tests/dfx/perf/scripts/run_diffusion_benchmark.py
+    - tests/dfx/perf/tests/test_wan22_i2v_vllm_omni.json
+
+  diffusion_wan22_reliability:
+    - *wan22
+    - tests/dfx/reliability/test_reliability_wan22.py
+
+  diffusion_image_to_video_doc:
+    - *wan22
+    - *hunyuan_video
+    - *ltx2
+    - *sana_video
+    - *lingbot_video
+    - examples/offline_inference/image_to_video/
+    - tests/examples/offline_inference/test_image_to_video.py
+
+  diffusion_cosmos3_function:
+    - *cosmos3
+    - tests/e2e/online_serving/test_cosmos3.py
+
+  diffusion_cosmos3_accuracy:
+    - *cosmos3
+    - tests/e2e/accuracy/test_cosmos3_similarity.py
+
+  diffusion_cosmos3_perf:
+    - *cosmos3
+    - tests/dfx/perf/scripts/run_diffusion_benchmark.py
+    - tests/dfx/perf/tests/test_cosmos3_vllm_omni.json
+
+  diffusion_qwen_image_function:
+    - *qwen_image
+    - tests/e2e/online_serving/test_qwen_image.py
+    - tests/e2e/online_serving/test_qwen_image_expansion.py
+
+  diffusion_qwen_image_accuracy:
+    - *qwen_image
+    - tests/e2e/accuracy/test_qwen_image.py
+    - tests/e2e/accuracy/test_diffusers_backend_similarity.py
+
+  diffusion_qwen_image_perf:
+    - *qwen_image
+    - tests/dfx/perf/scripts/run_diffusion_benchmark.py
+    - tests/dfx/perf/tests/test_qwen_image_vllm_omni.json
+
+  diffusion_text_to_image_doc:
+    - *qwen_image
+    - *z_image
+    - examples/offline_inference/text_to_image/
+    - examples/online_serving/text_to_image/
+    - tests/examples/offline_inference/test_text_to_image.py
+    - tests/examples/online_serving/test_text_to_image.py
+    - vllm_omni/diffusion/models/nextstep_1_1/
+    - vllm_omni/diffusion/models/longcat_image/
+    - vllm_omni/diffusion/models/ovis_image/
+    - vllm_omni/diffusion/models/omnigen2/
+    - vllm_omni/diffusion/models/sd3/
+    - vllm_omni/diffusion/models/flux/
+    - vllm_omni/diffusion/models/flux2/
+    - vllm_omni/diffusion/models/flux2_klein/
+    - vllm_omni/diffusion/models/hidream_image/
+    - vllm_omni/diffusion/models/krea2/
+    - vllm_omni/diffusion/models/lingbot_video/
+
+  diffusion_hunyuan_image3_function:
+    - *hunyuan_image3
+    - tests/e2e/offline_inference/test_hunyuanimage3_i2t_expansion.py
+
+  diffusion_hunyuan_image3_accuracy:
+    - *hunyuan_image3
+    - tests/e2e/accuracy/test_hunyuan_image3_pixel_accuracy.py
+
+  diffusion_hunyuan_image3_perf:
+    - *hunyuan_image3
+    - tests/dfx/perf/scripts/run_diffusion_benchmark.py
+    - tests/dfx/perf/tests/test_hunyuan_image_tp2_cfgp2.json
+    - tests/dfx/perf/tests/test_hunyuan_image_tp2_sp2.json
+    - tests/dfx/perf/tests/test_hunyuan_image_tp4.json
+
+  diffusion_hunyuan_image3_reliability:
+    - *hunyuan_image3
+    - tests/dfx/reliability/test_reliability_hunyuan_image.py
+
+  diffusion_minimax_h3_function:
+    - *minimax_h3
+    - tests/e2e/online_serving/test_minimax_h3_dlo_dp2_t2va.py
+    - tests/e2e/online_serving/minimax_h3/
+    - tests/diffusion/models/minimax_h3/
+    - vllm_omni/diffusion/lora/
+    - vllm_omni/diffusion/offloader/
+    - vllm_omni/diffusion/distributed/
+    - vllm_omni/entrypoints/openai/
+
+  diffusion_minimax_h3_accuracy:
+    - *minimax_h3
+    - tests/e2e/accuracy/minimax_h3/
+
+  diffusion_minimax_h3_perf:
+    - *minimax_h3
+    - tests/dfx/perf/scripts/run_diffusion_benchmark.py
+    - tests/dfx/perf/tests/test_minimax_h3_vllm_omni.json
+
+  diffusion_hunyuan_video_function:
+    - *hunyuan_video
+    - tests/e2e/online_serving/test_hunyuan_video_15_expansion.py
+
+  diffusion_hunyuan_video_accuracy:
+    - *hunyuan_video
+    - tests/e2e/accuracy/hunyuanvideo15_t2v/
+    - tests/e2e/accuracy/hunyuanvideo15_i2v/
+
+  diffusion_hunyuan_video_perf:
+    - *hunyuan_video
+    - tests/dfx/perf/scripts/run_diffusion_benchmark.py
+    - tests/dfx/perf/tests/test_hunyuanvideo15_t2v_vllm_omni.json
+    - tests/dfx/perf/tests/test_hunyuanvideo15_i2v_vllm_omni.json
+
+  diffusion_z_image_function:
+    - *z_image
+    - tests/e2e/online_serving/test_z_image.py
+    - tests/e2e/online_serving/test_zimage_expansion.py
+
+  diffusion_stable_audio_function:
+    - *stable_audio
+    - tests/e2e/offline_inference/test_stable_audio_expansion.py
+    - tests/e2e/online_serving/test_stable_audio_online_expansion.py
+
+  diffusion_lingbot_function:
+    - *lingbot_video
+    - *lingbot_world
+    - tests/e2e/online_serving/test_lingbot_video.py
+    - tests/e2e/online_serving/test_lingbot_video_moe.py
+    - tests/e2e/offline_inference/test_lingbot_world_v2.py
+
+
+  # Invalid-param jobs: model business code only, plus the reliability scripts.
+  reliability_invalid_param_h100:
+    - *qwen3_omni
+    - *minicpmo_4_5
+    - *qwen_image
+    - *wan22
+    - tests/dfx/reliability/invalid_param_test/
+
+  reliability_invalid_param_l4:
+    - *qwen3_tts
+    - *stable_audio
+    - tests/dfx/reliability/invalid_param_test/

.buildkite/common/scripts/upload_pipeline.py

@@ -10,8 +10,15 @@ Bootstrap mode (``bootstrap-upload-steps.yml``):
   - 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.
+Test pipeline mode (e.g. test-merge.yml, test-nightly.yml, test-weekly.yml):
+  - Drop steps whose ``source_file_dependencies`` do not match changed files
+    (string/list keys from ci_source_file_dependencies.yml, or inline path
+    prefixes). Filtering applies on **PR label** uploads only; ``main`` + env
+    schedule (NIGHTLY/WEEKLY/merge push) keeps every job and still strips the field.
+    If no job-key prefix matches, a change to the pipeline YAML being uploaded
+    or to a path under the ``source_filter_fallback`` registry key keeps every
+    job so command, env, and hardware edits can be validated before merge.
+    When any job-key prefix already matches, normal filtering wins.
   - Expand uploader-only ``mirror_hardwares`` into ``agents`` (+ optional ``image``
     for NPU) + ``plugins`` (see ci_mirror_hardwares.yml).
   - Omit ``mirror_hardwares`` to compose ``{chip}_{n}`` from pytest ``-m`` SKU
@@ -87,6 +94,10 @@ BOOTSTRAP_UPLOAD_IF_KEYS = {
 }
 E2E_GROUP_MARKER = "E2E Test"
 CI_MIRROR_HARDWARES_PATH = ROOT / ".buildkite/common/ci_mirror_hardwares.yml"
+CI_SOURCE_FILE_DEPENDENCIES_PATH = ROOT / ".buildkite/common/ci_source_file_dependencies.yml"
+# Registry key whose prefixes bypass source filtering. Paths live in
+# ci_source_file_dependencies.yml; do not attach this key to a job.
+SOURCE_FILTER_FALLBACK_KEY = "source_filter_fallback"
 CUDA_HF_TOKEN_ENV = "VLLM_CI_HF_TOKEN"
 CUDA_HF_TOKEN_EXPORT = f'if [ -n "$${{{CUDA_HF_TOKEN_ENV}:-}}" ]; then export HF_TOKEN="$${{{CUDA_HF_TOKEN_ENV}}}"; fi'
 
@@ -95,14 +106,7 @@ CUDA_HF_TOKEN_EXPORT = f'if [ -n "$${{{CUDA_HF_TOKEN_ENV}:-}}" ]; then export HF
 # ``*_UPLOAD_IF``: full gate for uploading that child pipeline.
 NIGHTLY_MAIN_IF = 'build.branch == "main" && build.env("NIGHTLY") == "1"'
 NIGHTLY_LABEL_IF = (
-    f"({NIGHTLY_MAIN_IF}) || "
-    '(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"'
-    "))"
+    f'({NIGHTLY_MAIN_IF}) || (build.branch != "main" && build.pull_request.labels includes "nightly-test")'
 )
 WEEKLY_E2E_IF = 'build.branch == "main" && build.env("WEEKLY") == "1"'
 WEEKLY_MAIN_IF = 'build.branch == "main" && (build.env("WEEKLY") == "1" || build.env("NON_CRITICAL") == "1")'
@@ -248,7 +252,7 @@ def _render_bootstrap_pipeline(
     return yaml.safe_dump(doc, sort_keys=False)
 
 
-# --- Test pipeline (test-ready.yml, test-merge.yml) ---
+# --- Test pipeline (test-ready.yml, test-merge.yml, test-nightly.yml) ---
 
 
 @lru_cache(maxsize=1)
@@ -264,6 +268,117 @@ def _load_mirror_hardwares() -> dict[str, dict[str, Any]]:
     return presets
 
 
+@lru_cache(maxsize=1)
+def _load_source_file_dependencies() -> dict[str, list[str]]:
+    def flatten(value: Any, *, key: str) -> list[str]:
+        """Flatten YAML-anchor nested lists into a de-duplicated prefix list."""
+        if isinstance(value, str):
+            if not value.strip():
+                raise ValueError(f"empty path in source_file_dependencies[{key!r}]")
+            return [value]
+        if isinstance(value, list):
+            flattened: list[str] = []
+            seen: set[str] = set()
+            for item in value:
+                for path in flatten(item, key=key):
+                    if path not in seen:
+                        seen.add(path)
+                        flattened.append(path)
+            return flattened
+        raise ValueError(
+            f"source_file_dependencies[{key!r}] must be a list of path prefixes, got {type(value).__name__}",
+        )
+
+    if not CI_SOURCE_FILE_DEPENDENCIES_PATH.is_file():
+        raise FileNotFoundError(
+            f"missing CI source_file_dependencies registry: {CI_SOURCE_FILE_DEPENDENCIES_PATH}",
+        )
+    doc = yaml.safe_load(CI_SOURCE_FILE_DEPENDENCIES_PATH.read_text(encoding="utf-8"))
+    if not isinstance(doc, dict):
+        raise ValueError(f"invalid CI source_file_dependencies registry: {CI_SOURCE_FILE_DEPENDENCIES_PATH}")
+    presets = doc.get("source_file_dependencies")
+    if not isinstance(presets, dict):
+        raise ValueError(f"source_file_dependencies must be a mapping in {CI_SOURCE_FILE_DEPENDENCIES_PATH}")
+    loaded: dict[str, list[str]] = {}
+    for key, value in presets.items():
+        if not isinstance(key, str) or not key.strip():
+            raise ValueError(
+                f"source_file_dependencies keys must be non-empty strings in {CI_SOURCE_FILE_DEPENDENCIES_PATH}",
+            )
+        loaded[key] = flatten(value, key=key)
+    return loaded
+
+
+_REGISTRY_KEY_RE = re.compile(r"^[a-z][a-z0-9_]*$")
+
+
+def _parse_command_text(step: dict[str, Any]) -> str:
+    """Parse step ``commands`` / ``command`` into a single string."""
+    raw = step.get("commands", step.get("command"))
+    if raw is None:
+        return ""
+    if isinstance(raw, str):
+        return raw
+    if isinstance(raw, list):
+        return "\n".join(str(item) for item in raw if item is not None)
+    return str(raw)
+
+
+def _resolve_source_file_dependencies(step: dict[str, Any]) -> list[str] | None:
+    """Expand a registry key (or list of keys / inline path prefixes)."""
+    deps = step.get("source_file_dependencies")
+    if deps is None:
+        return None
+
+    def dedupe(*groups: list[str]) -> list[str]:
+        merged: list[str] = []
+        seen: set[str] = set()
+        for group in groups:
+            for path in group:
+                if path not in seen:
+                    seen.add(path)
+                    merged.append(path)
+        return merged
+
+    def lookup(key: str) -> list[str]:
+        if key == SOURCE_FILTER_FALLBACK_KEY:
+            raise ValueError(
+                f"source_file_dependencies {key!r} bypasses filtering and cannot be attached to a step "
+                f"({_get_step_label(step)!r})",
+            )
+        registry = _load_source_file_dependencies()
+        paths = registry.get(key)
+        if paths is None:
+            known = ", ".join(sorted(registry))
+            raise ValueError(
+                f"unknown source_file_dependencies {key!r} in step {_get_step_label(step)!r}; known: {known}",
+            )
+        return list(paths)
+
+    prefixes: list[str]
+    if isinstance(deps, str):
+        prefixes = lookup(deps) if _REGISTRY_KEY_RE.fullmatch(deps) else [deps]
+    elif isinstance(deps, list):
+        if not all(isinstance(item, str) for item in deps):
+            raise ValueError(
+                f"source_file_dependencies must be a string key or list of strings in step {_get_step_label(step)!r}",
+            )
+        keyish = [bool(_REGISTRY_KEY_RE.fullmatch(item)) for item in deps]
+        if deps and all(keyish):
+            prefixes = dedupe(*(lookup(key) for key in deps))
+        elif any(keyish):
+            raise ValueError(
+                f"source_file_dependencies in step {_get_step_label(step)!r} mixes registry keys and path prefixes",
+            )
+        else:
+            prefixes = list(deps)
+    else:
+        raise ValueError(
+            f"source_file_dependencies must be a string key or list in step {_get_step_label(step)!r}",
+        )
+    return prefixes
+
+
 @lru_cache(maxsize=1)
 def _cuda_mirror_chips() -> tuple[str, ...]:
     """Lowercase CUDA SKUs that have at least one ``{chip}_{n}`` preset.
@@ -278,7 +393,7 @@ def _cuda_mirror_chips() -> tuple[str, ...]:
     return tuple(sorted(chips, key=lambda chip: (-len(chip), chip)))
 
 
-def _read_cards_marks(expr: str) -> tuple[set[int], bool]:
+def _parse_cards_marks(expr: str) -> tuple[set[int], bool]:
     """Parse registered ``cards_n`` / ``not cards_n`` from a pytest ``-m`` expr.
 
     Returns positive card counts and whether any ``not cards_*`` is present.
@@ -295,8 +410,8 @@ def _read_cards_marks(expr: str) -> tuple[set[int], bool]:
     return positives, has_not_cards
 
 
-def _read_hardware_marks(expr: str) -> set[str]:
-    """Return lowercase positive CUDA SKUs that have a mirror preset.
+def _parse_hardware_marks(expr: str) -> set[str]:
+    """Parse lowercase positive CUDA SKUs that have a mirror preset.
 
     ``not H100`` is ignored. SKUs with no ``{chip}_*`` preset (e.g. H200) are dropped.
     """
@@ -338,36 +453,22 @@ def _get_mirror_hw_selector() -> str:
     return selector
 
 
-def _read_pytest_marks(commands: Any) -> tuple[set[str], int | Literal["max"] | None]:
-    """Read pytest ``-m`` from step commands: CUDA SKU chips and cards count.
+def _parse_pytest_marks(step: dict[str, Any]) -> tuple[set[str], int | Literal["max"] | None]:
+    """Parse pytest ``-m`` from step commands: CUDA SKU chips and cards count.
 
     *chips* are lowercase SKUs from positive markers (``not H100`` is ignored).
     *cards* is the max positive ``cards_n``, ``"max"`` when only ``not cards_*``
     is present, or ``None``.
     """
-    chunks: list[str] = []
-
-    def _collect(value: Any) -> None:
-        if value is None:
-            return
-        if isinstance(value, str):
-            chunks.append(value)
-        elif isinstance(value, list):
-            for part in value:
-                _collect(part)
-        else:
-            chunks.append(str(value))
-
-    _collect(commands)
-    text = "\n".join(chunks)
+    text = _parse_command_text(step)
 
     chips: set[str] = set()
     positives: set[int] = set()
     has_not_cards = False
     for match in _PYTEST_MARKER_ARG.finditer(text):
         expr = match.group(1) or match.group(2) or match.group(3) or ""
-        chips |= _read_hardware_marks(expr)
-        card_counts, not_cards = _read_cards_marks(expr)
+        chips |= _parse_hardware_marks(expr)
+        card_counts, not_cards = _parse_cards_marks(expr)
         positives.update(card_counts)
         has_not_cards = has_not_cards or not_cards
 
@@ -484,7 +585,7 @@ def _expand_mirror_hardwares(step: dict[str, Any]) -> dict[str, Any] | None:
     if "mirror_hardwares" not in step:
         if has_pool:
             return step
-        chips, cards = _read_pytest_marks(step.get("commands"))
+        chips, cards = _parse_pytest_marks(step)
         if not chips and cards is None:
             return step
         preset_name = _compose_mirror_hardware_name(chips, cards, step_label=step_label)
@@ -552,11 +653,7 @@ def _process_test_steps(
             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}",
-            )
+        deps = _resolve_source_file_dependencies(step)
         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
@@ -595,10 +692,25 @@ def _select_e2e_group_steps(steps: list[Any]) -> list[Any]:
     return selected
 
 
+def _any_source_dependency_match(steps: list[Any], changed_files: list[str]) -> bool:
+    """True when any step with ``source_file_dependencies`` matches *changed_files*."""
+    for step in steps:
+        if not isinstance(step, dict):
+            continue
+        deps = _resolve_source_file_dependencies(step)
+        if deps is not None and _match_source_file(changed_files, deps):
+            return True
+        nested = step.get("steps")
+        if isinstance(nested, list) and _any_source_dependency_match(nested, changed_files):
+            return True
+    return False
+
+
 def _render_test_pipeline(
     doc: dict[str, Any],
     changed_files: list[str] | None,
     *,
+    pipeline_path: Path | None = None,
     e2e_only: bool = False,
 ) -> dict[str, Any]:
     """Filter steps by PR diff and strip uploader-only ``source_file_dependencies`` metadata."""
@@ -611,6 +723,13 @@ def _render_test_pipeline(
         return doc
     if e2e_only:
         steps = _select_e2e_group_steps(steps)
+    # Bypass is a fallback: only when no job-key prefix matched.
+    if changed_files is not None and pipeline_path is not None:
+        if not _any_source_dependency_match(steps, changed_files):
+            bypass = _source_filter_fallback_reason(changed_files, pipeline_path)
+            if bypass is not None:
+                _log(f"keep all jobs (no source_file_dependencies match; bypassed by {bypass})")
+                changed_files = None
     steps = _process_test_steps(steps, changed_files)
     return {**doc, "steps": steps}
 
@@ -618,6 +737,63 @@ def _render_test_pipeline(
 # --- Entry (read file → bootstrap or test render → YAML string) ---
 
 
+def _repo_relative_posix(path: Path) -> str:
+    resolved = path.resolve()
+    try:
+        return resolved.relative_to(ROOT).as_posix()
+    except ValueError:
+        return path.as_posix().replace("\\", "/")
+
+
+def _source_filter_fallback_prefixes() -> list[str]:
+    """Shared uploader/registry prefixes from ``source_filter_fallback``. Not a job key."""
+    registry = _load_source_file_dependencies()
+    prefixes = registry.get(SOURCE_FILTER_FALLBACK_KEY)
+    if not prefixes:
+        raise ValueError(
+            f"source_file_dependencies[{SOURCE_FILTER_FALLBACK_KEY!r}] must list shared uploader paths "
+            f"in {CI_SOURCE_FILE_DEPENDENCIES_PATH}",
+        )
+    return prefixes
+
+
+def _source_filter_fallback_reason(changed_files: list[str] | None, pipeline_path: Path) -> str | None:
+    """Return the changed path that should disable source filtering, if any."""
+    if not changed_files:
+        return None
+    changed = set(changed_files)
+    pipeline_rel = _repo_relative_posix(pipeline_path)
+    if pipeline_rel in changed:
+        return pipeline_rel
+    prefixes = _source_filter_fallback_prefixes()
+    for path in changed_files:
+        if _match_source_file([path], prefixes):
+            return path
+    return None
+
+
+def _changed_files_for_source_filter(
+    ctx,
+    *,
+    force_all: bool,
+    e2e_only: bool,
+) -> list[str] | None:
+    """Return the diff to filter against, or None to keep every step.
+
+    ``source_file_dependencies`` is label-only: scheduled ``main`` uploads
+    (NIGHTLY/WEEKLY/post-merge) run the full pipeline. ``--all`` / ``--e2e``
+    also disable filtering. Pipeline YAML / ``source_filter_fallback`` matches
+    are applied later in ``_render_test_pipeline`` only when no job-key prefix
+    already matched.
+    """
+    if force_all or e2e_only:
+        return None
+    if os.environ.get("BUILDKITE_BRANCH", "") == "main":
+        _log("main branch: keep all jobs (source_file_dependencies is label-only)")
+        return None
+    return ctx.changed_files
+
+
 def _render_pipeline(
     path: Path,
     *,
@@ -635,13 +811,18 @@ def _render_pipeline(
 
     text = path.read_text(encoding="utf-8")
     ctx = resolve_ci_context_from_git()
-    changed_files = None if force_all or e2e_only else ctx.changed_files
+    changed_files = _changed_files_for_source_filter(ctx, force_all=force_all, e2e_only=e2e_only)
 
     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)
+    doc = _render_test_pipeline(
+        doc,
+        changed_files,
+        pipeline_path=path,
+        e2e_only=e2e_only,
+    )
     return yaml.safe_dump(doc, sort_keys=False)
 
 

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

@@ -22,34 +22,48 @@ steps:
     agents:
       queue: "cpu_queue_premerge"
 
-  # L3 Test — PR merge-test label (diff-aware) or main+WEEKLY=1 (--e2e, full E2E group)
+  # L3 Test — PR merge-test label (diff-aware) or main (full pipeline / WEEKLY --e2e)
   - label: "Upload Merge Pipeline"
     depends_on: image-build
     key: upload-merge-pipeline
     commands:
       - |
         EXTRA=""
-        if [ "${WEEKLY:-}" = "1" ] && [ "${BUILDKITE_BRANCH}" = "main" ]; then
-          EXTRA="--e2e"
+        if [ "${BUILDKITE_BRANCH}" = "main" ]; then
+          if [ "${WEEKLY:-}" = "1" ]; then
+            EXTRA="--e2e"
+          else
+            EXTRA="--all"
+          fi
         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)
+  # L4 Test — main+NIGHTLY=1 (full pipeline), or PR nightly-test label (diff-aware)
   - 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
+      - |
+        EXTRA=""
+        if [ "${NIGHTLY:-}" = "1" ] && [ "${BUILDKITE_BRANCH}" = "main" ]; then
+          EXTRA="--all"
+        fi
+        python3 .buildkite/common/scripts/upload_pipeline.py --upload $$EXTRA .buildkite/cuda/test-nightly.yml
     agents:
       queue: "cpu_queue_premerge"
 
-  # L5 Test — main+WEEKLY=1 / NON_CRITICAL=1 (scheduled), or PR with weekly-test label
+  # L5 Test — main+WEEKLY=1 / NON_CRITICAL=1 (full pipeline), or PR weekly-test label (diff-aware)
   - 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
+      - |
+        EXTRA=""
+        if [ "${BUILDKITE_BRANCH}" = "main" ]; then
+          EXTRA="--all"
+        fi
+        python3 .buildkite/common/scripts/upload_pipeline.py --upload $$EXTRA .buildkite/cuda/test-weekly.yml
     agents:
       queue: "cpu_queue_premerge"

.buildkite/cuda/test-merge.yml

@@ -78,21 +78,7 @@ steps:
     depends_on: upload-merge-pipeline
     steps:
       - label: "TTS · Qwen3-TTS CustomVoice Test"
-        source_file_dependencies:
-          - tests/e2e/features/prefill_phase/
-          - vllm_omni/worker/gpu_model_runner.py
-          - tests/helpers/media.py
-          - 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/models/common/qwen3_code_predictor.py
-          - vllm_omni/model_executor/models/common/snake_activation.py
-          - vllm_omni/model_executor/models/common/alias_free_activation.py
-          - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
-          - vllm_omni/deploy/qwen3_tts.yaml
-          - vllm_omni/entrypoints/openai/serving_speech.py
-          - vllm_omni/entrypoints/openai/tts_adapters/
-          - vllm_omni/engine/stage_pool.py
+        source_file_dependencies: tts_qwen3_tts_function
         commands:
           - |
             timeout 40m bash -c "
@@ -103,21 +89,7 @@ steps:
         mirror_hardwares: l4_1
 
       - label: "TTS · Qwen3-TTS Base Test"
-        source_file_dependencies:
-          - tests/helpers/media.py
-          - 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/models/common/qwen3_code_predictor.py
-          - vllm_omni/model_executor/models/common/snake_activation.py
-          - vllm_omni/model_executor/models/common/alias_free_activation.py
-          - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
-          - vllm_omni/deploy/qwen3_tts.yaml
-          - vllm_omni/entrypoints/openai/serving_speech.py
-          - vllm_omni/entrypoints/openai/tts_adapters/
-          - vllm_omni/engine/stage_pool.py
-          - .buildkite/common/scripts/run_cov_split.sh
-          - pyproject.toml
+        source_file_dependencies: tts_qwen3_tts_cov
         # 40 -> 60: the coverage split runs the model twice.
         timeout_in_minutes: 60
         commands:
@@ -132,36 +104,14 @@ steps:
         mirror_hardwares: l4_1
 
       - label: "Omni · Qwen3-Omni Test"
-        source_file_dependencies:
-          - tests/e2e/offline_inference/test_qwen3_omni.py
-          - tests/e2e/offline_inference/test_qwen3_omni_colocate_async.py
-          - tests/e2e/online_serving/test_qwen3_omni.py
-          - tests/helpers/runtime.py
-          - vllm_omni/entrypoints/openai/serving_chat.py
-          - vllm_omni/model_executor/models/qwen3_omni/
-          - vllm_omni/model_executor/models/common/qwen3_code_predictor.py
-          - vllm_omni/model_executor/models/common/snake_activation.py
-          - vllm_omni/model_executor/models/qwen2_5_omni/qwen2_5_omni_thinker.py
-          - vllm_omni/model_executor/models/qwen3_tts/cuda_graph_decoder_wrapper.py
-          - vllm_omni/model_executor/stage_input_processors/qwen3_omni.py
-          - vllm_omni/deploy/qwen3_omni_moe.yaml
-          - vllm_omni/deploy/qwen3_omni_moe_thinking.yaml
+        source_file_dependencies: omni_qwen3_omni_function
         timeout_in_minutes: 50
         commands:
           - 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'
         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/transformers_utils/chat_templates/minicpmo45_native.jinja
-          - vllm_omni/model_executor/models/minicpmo_4_5/
-          - vllm_omni/model_executor/models/step_audio2/
-          - vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
-          - vllm_omni/model_executor/models/cosyvoice3/utils.py
-          - vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
-          - vllm_omni/deploy/minicpmo_4_5.yaml
+        source_file_dependencies: omni_minicpmo_4_5_function
         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'
@@ -174,59 +124,14 @@ steps:
         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_server_vad.py
-          - tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py
-          - vllm_omni/deploy/minicpmo_4_5.yaml
-          - tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py
-          - vllm_omni/engine/duplex/
-          - vllm_omni/entrypoints/duplex/
-          # Public duplex client library + its unit suites: client-side
-          # changes must re-run the duplex e2e group. The live client probe
-          # (test_duplex_client_live.py, single GPU, core tier) runs in the
-          # ready pipeline's duplex group.
-          - vllm_omni/clients/
-          - tests/clients/
-          - vllm_omni/entrypoints/duplex_request_client.py
-          - vllm_omni/outputs/duplex.py
-          - vllm_omni/model_executor/duplex_sampling.py
-          - tests/engine/duplex/
-          - tests/entrypoints/duplex/
-          - tests/model_executor/models/minicpmo_4_5/duplex/
-          # Legacy Realtime probe client + video stacking used by the e2e drivers.
-          - vllm_omni/experimental/fullduplex/
-          - vllm_omni/model_executor/models/minicpmo_4_5/
-          - vllm_omni/model_executor/models/step_audio2/
-          - vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
-          - vllm_omni/model_executor/models/cosyvoice3/utils.py
-          - 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/engine/orchestrator.py
-          - vllm_omni/entrypoints/cli/serve.py
-          - vllm_omni/entrypoints/openai/api_server.py
-          - vllm_omni/entrypoints/openai/duplex_capability.py
-          - vllm_omni/config/stage_config.py
+        source_file_dependencies: omni_minicpmo_4_5_duplex_function
         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: "Diffusion · Qwen Image Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen_image.py
-          - vllm_omni/diffusion/models/qwen_image/
-          - vllm_omni/diffusion/models/dmd2/
-          - vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_qwenimage.py
+        source_file_dependencies: diffusion_qwen_image_function
         commands:
           - |
             timeout 40m bash -c '
@@ -236,11 +141,7 @@ steps:
         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/
-          - vllm_omni/diffusion/models/dmd2/
+        source_file_dependencies: diffusion_wan22_function
         commands:
           - |
             timeout 40m bash -c "
@@ -250,9 +151,7 @@ steps:
         mirror_hardwares: h100_1
 
       - label: "Diffusion · HunyuanVideo-1.5 Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_hunyuan_video_15_expansion.py
-          - vllm_omni/diffusion/models/hunyuan_video/
+        source_file_dependencies: diffusion_hunyuan_video_function
         commands:
           - |
             timeout 40m bash -c "
@@ -262,17 +161,7 @@ steps:
         mirror_hardwares: h100_1
 
       - label: "Diffusion · MiniMax-H3 L3 DLO DP2 and FastH3"
-        source_file_dependencies:
-          - tests/e2e/online_serving/minimax_h3/
-          - tests/helpers/assertions.py
-          - tests/helpers/mark.py
-          - tests/helpers/media.py
-          - tests/helpers/runtime.py
-          - vllm_omni/diffusion/models/minimax_h3/
-          - vllm_omni/diffusion/lora/
-          - vllm_omni/diffusion/offloader/
-          - vllm_omni/diffusion/distributed/
-          - vllm_omni/entrypoints/openai/
+        source_file_dependencies: diffusion_minimax_h3_function
         # Keep four server lifecycles in one Buildkite job, but never in one
         # pytest process. DLO uses multiprocessing shared-memory queues; the
         # parent's resource_tracker can retain a stale /psm_* entry during

.buildkite/cuda/test-nightly.yml

@@ -12,26 +12,34 @@ 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"
+    if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
     steps:
 
       - label: ":full_moon: Omni · Function Test with H100 · Single-GPU"
+        source_file_dependencies:
+          - omni_qwen3_omni_function
+          - omni_minicpmo_4_5_function
         timeout_in_minutes: 120
         commands:
           - pytest -sv tests/e2e --run-level "full_model" -m "full_model and H100 and B200 and omni and cards_1" --ignore=tests/e2e/accuracy --ignore=tests/e2e/online_serving/test_minicpmo_4_5_duplex_expansion.py
 
       - label: ":full_moon: Omni · Function Test with H100 · 2-GPU"
+        source_file_dependencies:
+          - omni_qwen3_omni_function
+          - omni_minicpmo_4_5_function
         timeout_in_minutes: 90
         commands:
           - pytest -sv tests/e2e --run-level "full_model" -m "full_model and H100 and B200 and omni and cards_2" --ignore=tests/e2e/accuracy --ignore=tests/e2e/online_serving/test_qwen3_omni_multi_replicas.py
 
       - label: ":full_moon: Omni · MiniCPM-o 4.5 Duplex Test"
+        source_file_dependencies: omni_minicpmo_4_5_duplex_function
         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 and cards_1" --run-level "full_model"
         mirror_hardwares: h100_1
 
       - label: ":full_moon: Omni · Doc Test with L4 · 4-GPU"
+        source_file_dependencies: omni_qwen2_5_omni_doc
         timeout_in_minutes: 90
         commands:
           - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
@@ -39,12 +47,14 @@ steps:
         mirror_hardwares: l4_4
 
       - label: ":full_moon: Omni · Doc Test with H100 · 2-GPU"
+        source_file_dependencies: omni_qwen3_omni_doc
         timeout_in_minutes: 90
         commands:
           - pytest -s -v tests/examples/ -m "full_model and omni and H100 and cards_2" --run-level "full_model"
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Omni · Accuracy Test"
+        source_file_dependencies: omni_qwen3_omni_accuracy
         timeout_in_minutes: 180
         commands:
           - export SEED_TTS_WER_EVAL=1
@@ -58,6 +68,7 @@ steps:
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Omni · MiniCPM-o 4.5 · Accuracy Test"
+        source_file_dependencies: omni_minicpmo_4_5_accuracy
         timeout_in_minutes: 180
         commands:
           - export SEED_TTS_WER_EVAL=1
@@ -71,6 +82,7 @@ steps:
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Omni · Perf Test · No Async Chunk"
+        source_file_dependencies: omni_qwen3_omni_perf
         key: nightly-omni-performance-no-async-chunk
         timeout_in_minutes: 300
         commands:
@@ -84,6 +96,7 @@ steps:
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Omni · Perf Test · Async Chunk"
+        source_file_dependencies: omni_qwen3_omni_perf
         key: nightly-omni-performance-async-chunk
         timeout_in_minutes: 180
         commands:
@@ -97,19 +110,21 @@ steps:
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Omni · MiniCPM-o 4.5 · Perf Test"
+        source_file_dependencies: omni_minicpmo_4_5_perf
         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
+            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_minicpmo_4_5.json -m "H100 and cards_1"
             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"
+        source_file_dependencies: omni_minicpmo_4_5_duplex_perf
         key: nightly-omni-performance-minicpmo-4-5-duplex-seed-tts
         timeout_in_minutes: 180
         commands:
@@ -123,6 +138,7 @@ steps:
         mirror_hardwares: h100_1
 
       - label: ":full_moon: Omni · Multi-Replica Startup Test with 4x H100"
+        source_file_dependencies: omni_qwen3_omni_function
         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"
@@ -131,10 +147,11 @@ steps:
   - 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"
+    if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
     steps:
 
       - label: ":full_moon: TTS · Function Test with L4"
+        source_file_dependencies: tts_qwen3_tts_function
         timeout_in_minutes: 120
         commands:
           - export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
@@ -144,6 +161,7 @@ steps:
         mirror_hardwares: l4_1
 
       - label: ":full_moon: TTS · Perf Test · Single-GPU"
+        source_file_dependencies: tts_qwen3_tts_perf
         key: nightly-tts-performance-single
         timeout_in_minutes: 180
         commands:
@@ -158,6 +176,7 @@ steps:
         mirror_hardwares: h100_1
 
       - label: ":full_moon: TTS · Perf Test · 2-GPU"
+        source_file_dependencies: tts_qwen3_tts_perf
         key: nightly-tts-performance-2gpu
         timeout_in_minutes: 180
         commands:
@@ -180,6 +199,7 @@ steps:
     steps:
 
       - label: ":full_moon: Tiny Model Tests · Diffusion (Multi-GPU accelerations) · 2-GPU"
+        source_file_dependencies: diffusion_tiny_model
         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.
@@ -193,6 +213,7 @@ steps:
         mirror_hardwares: l4_2
 
       - label: ":full_moon: Tiny Model Tests · Diffusion (Multi-GPU accelerations) · 4-GPU"
+        source_file_dependencies: diffusion_tiny_model
         timeout_in_minutes: 30
         # CFG+TP extra_test_groups request 2×2=4 devices (see get_required_device_count).
         commands:
@@ -204,11 +225,11 @@ steps:
     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"
+      build.pull_request.labels includes "nightly-test"
     steps:
 
       - label: ":full_moon: Diffusion X2I(&A&T) · Function Test with H100 · Single-GPU"
+        source_file_dependencies: diffusion_qwen_image_function
         timeout_in_minutes: 120
         commands:
           - >-
@@ -219,6 +240,7 @@ steps:
         mirror_hardwares: h100_1
 
       - label: ":full_moon: Diffusion X2I(&A&T) · Function Test with H100 · 2-GPU"
+        source_file_dependencies: diffusion_qwen_image_function
         timeout_in_minutes: 120
         commands:
           - >-
@@ -228,30 +250,26 @@ steps:
             --run-level "full_model"
         mirror_hardwares: h100_2
 
-      - label: ":full_moon: Diffusion X2I(&A&T) · Boogu Edit CFG · 3-GPU"
+      - label: ":full_moon: Diffusion X2I(&A&T) · Z-Image Function Test · L4 · 4-GPU"
+        source_file_dependencies: diffusion_z_image_function
         timeout_in_minutes: 120
         commands:
           - >-
             pytest -sv
-            tests/e2e/online_serving/test_boogu_image_edit_expansion.py
-            -k "test_double_guidance_cfg_parallel and cfg_parallel_3_full"
-            -m "slow and diffusion and cuda and H100 and cards_3"
+            tests/e2e/online_serving/test_zimage_expansion.py
+            -m "full_model and diffusion and L4 and cards_4"
             --run-level "full_model"
-        mirror_hardwares: h100_3
-
-      - label: ":full_moon: Diffusion X2I(&A&T) · Function Test with L4 · 4-GPU"
-        timeout_in_minutes: 120
-        commands:
-          - pytest -sv tests/e2e/ -k "not test_wan and not hunyuan" -m "full_model and diffusion and L4 and cards_4" --run-level "full_model" --ignore=tests/e2e/accuracy
         mirror_hardwares: l4_4
 
       - label: ":full_moon: Diffusion X2I(&A&T) · Doc Test"
+        source_file_dependencies: diffusion_text_to_image_doc
         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"
+        source_file_dependencies: diffusion_qwen_image_accuracy
         timeout_in_minutes: 180
         commands:
           - export VLLM_HTTP_TIMEOUT_KEEP_ALIVE=120
@@ -260,6 +278,7 @@ steps:
         mirror_hardwares: h100_1
 
       - label: ":full_moon: HunyuanImage3-DIT · Accuracy Test"
+        source_file_dependencies: diffusion_hunyuan_image3_accuracy
         timeout_in_minutes: 180
         commands:
           - export HUNYUAN_IMAGE3_MODEL="tencent/HunyuanImage-3.0-Instruct"
@@ -267,13 +286,8 @@ steps:
           - 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: HiDream-O1-Image · Accuracy Test"
-        timeout_in_minutes: 180
-        commands:
-          - pytest -s -v tests/e2e/accuracy/test_hidream_o1_image.py -m full_model --run-level full_model
-        mirror_hardwares: h100_2
-
       - label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image · Single-GPU"
+        source_file_dependencies: diffusion_qwen_image_perf
         key: nightly-diffusion-x2iat-performance-qwen-image-single
         timeout_in_minutes: 180
         commands:
@@ -289,6 +303,7 @@ steps:
         mirror_hardwares: h100_1
 
       - label: ":full_moon: Diffusion X2I(&A&T) · Perf Test · Qwen-Image · 4-GPU"
+        source_file_dependencies: diffusion_qwen_image_perf
         key: nightly-diffusion-x2iat-performance-qwen-image-4gpu
         timeout_in_minutes: 180
         commands:
@@ -309,59 +324,73 @@ steps:
     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"
+      build.pull_request.labels includes "nightly-test"
     steps:
 
       - label: ":full_moon: Diffusion X2V · Wan2.2 T2V Function Test · Single-GPU"
+        source_file_dependencies: diffusion_wan22_function
         timeout_in_minutes: 90
         commands:
           - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "t2v" -m "full_model and cuda and H100 and cards_1" --run-level "full_model"
         mirror_hardwares: h100_1
 
       - label: ":full_moon: Diffusion X2V · Wan2.2 T2V Function Test · 2-GPU"
+        source_file_dependencies: diffusion_wan22_function
         timeout_in_minutes: 90
         commands:
           - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "t2v" -m "full_model and cuda and H100 and cards_2" --run-level "full_model"
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Diffusion X2V · Wan2.2 I2V/TI2V Function Test · Single-GPU"
+        source_file_dependencies: diffusion_wan22_function
         timeout_in_minutes: 90
         commands:
           - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "i2v" -m "full_model and cuda and H100 and cards_1" --run-level "full_model"
         mirror_hardwares: h100_1
 
       - label: ":full_moon: Diffusion X2V · Wan2.2 I2V/TI2V Function Test · 2-GPU"
+        source_file_dependencies: diffusion_wan22_function
         timeout_in_minutes: 90
         commands:
           - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "i2v" -m "full_model and cuda and H100 and cards_2" --run-level "full_model"
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Diffusion X2V · HunyuanVideo-1.5 Function Test"
+        source_file_dependencies: diffusion_hunyuan_video_function
         timeout_in_minutes: 90
         commands:
           - pytest -s -v tests/e2e/online_serving/test_hunyuan_video_15_expansion.py -m "full_model and cuda" --run-level "full_model"
         mirror_hardwares: h100_2
 
-      - label: ":full_moon: Diffusion X2V · MAGI-2 Preview Serving Smoke"
-        timeout_in_minutes: 180
+      - label: ":full_moon: Diffusion X2V · LingBot Function Test"
+        source_file_dependencies: diffusion_lingbot_function
+        timeout_in_minutes: 120
         commands:
-          - pytest -s -v tests/e2e/online_serving/test_magi2.py -m "advanced_model and diffusion and cuda and H100 and cards_4" --run-level "advanced_model"
-        mirror_hardwares: h100_4
+          - >-
+            pytest -s -v
+            tests/e2e/online_serving/test_lingbot_video.py
+            tests/e2e/online_serving/test_lingbot_video_moe.py
+            tests/e2e/offline_inference/test_lingbot_world_v2.py
+            -m "full_model and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
 
       - label: ":full_moon: Diffusion X2V · Doc Test"
+        source_file_dependencies: diffusion_image_to_video_doc
         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"
+      - label: ":full_moon: Diffusion X2V · Wan2.2 Autoround Function Test"
+        source_file_dependencies: diffusion_wan22_function
         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"
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Diffusion X2V · Wan2.2 Accuracy Test"
+        source_file_dependencies: diffusion_wan22_accuracy
         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
@@ -369,12 +398,14 @@ steps:
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Diffusion X2V · MiniMax H3 I2VA/Ref2VA Accuracy Test"
+        source_file_dependencies: diffusion_minimax_h3_accuracy
         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"
+      - label: ":full_moon: Diffusion X2V · HunyuanVideo-1.5 Accuracy Test"
+        source_file_dependencies: diffusion_hunyuan_video_accuracy
         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
@@ -382,6 +413,7 @@ steps:
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Diffusion X2V · Perf Test · Single-GPU"
+        source_file_dependencies: diffusion_wan22_perf
         key: nightly-diffusion-x2v-performance-single
         timeout_in_minutes: 180
         commands:
@@ -396,6 +428,9 @@ steps:
         mirror_hardwares: h100_1
 
       - label: ":full_moon: Diffusion X2V · Perf Test · 2-GPU"
+        source_file_dependencies:
+          - diffusion_wan22_perf
+          - diffusion_cosmos3_perf
         key: nightly-diffusion-x2v-performance-2gpu
         timeout_in_minutes: 180
         commands:
@@ -414,6 +449,7 @@ steps:
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Diffusion X2V · Perf Test · HunyuanVideo-1.5"
+        source_file_dependencies: diffusion_hunyuan_video_perf
         key: nightly-diffusion-x2v-performance-hunyuanvideo15
         timeout_in_minutes: 180
         commands:
@@ -431,6 +467,7 @@ steps:
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Diffusion X2V · Perf Test · MiniMax-H3"
+        source_file_dependencies: diffusion_minimax_h3_perf
         key: nightly-diffusion-x2v-performance-minimax-h3
         timeout_in_minutes: 180
         commands:
@@ -450,54 +487,63 @@ steps:
     if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
     steps:
       - label: ":full_moon: Diffusion · Distributed Test with L4 · 2-GPU"
+        source_file_dependencies: diffusion_distributed_attention
         timeout_in_minutes: 60
         commands:
           - pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4 and cards_2' --run-level "full_model"
         mirror_hardwares: l4_2
 
       - label: ":full_moon: Diffusion · Distributed Test with L4 · 3-GPU"
+        source_file_dependencies: diffusion_distributed_attention
         timeout_in_minutes: 60
         commands:
           - pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4 and cards_3' --run-level "full_model"
         mirror_hardwares: l4_3
 
       - label: ":full_moon: Diffusion · Distributed Test with L4 · 4-GPU"
+        source_file_dependencies: diffusion_distributed_attention
         timeout_in_minutes: 60
         commands:
           - pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and L4 and cards_4' --run-level "full_model"
         mirror_hardwares: l4_4
 
       - label: ":full_moon: Diffusion · Distributed Test with H100 · 2-GPU"
+        source_file_dependencies: diffusion_distributed_attention
         timeout_in_minutes: 60
         commands:
           - pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and H100 and cards_2' --run-level "full_model"
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Diffusion · Distributed Test with H100 · 4-GPU"
+        source_file_dependencies: diffusion_distributed_attention
         timeout_in_minutes: 60
         commands:
           - pytest -sv tests/diffusion/distributed/ -m 'full_model and cuda and H100 and cards_4' --run-level "full_model"
         mirror_hardwares: h100_4
 
       - label: ":full_moon: Diffusion · Offloader Test"
+        source_file_dependencies: diffusion_offloader
         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"
+        source_file_dependencies: diffusion_quantization
         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"
+        source_file_dependencies: diffusion_minimax_h3_function
         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"
+        source_file_dependencies: diffusion_quantization
         timeout_in_minutes: 60
         commands:
           - pip install "vllm-gguf-plugin==0.0.4"

.buildkite/cuda/test-ready.yml

@@ -54,16 +54,19 @@ steps:
         mirror_hardwares: l4_1
 
       - label: "Diffusion · Distributed Test · Single-GPU"
+        source_file_dependencies: diffusion_distributed_attention
         commands:
           - timeout 20m pytest -sv tests/diffusion/distributed -m 'core_model and cuda and L4 and cards_1' --run-level "core_model"
         mirror_hardwares: l4_1
 
       - label: "Diffusion · Distributed Test · 2-GPU"
+        source_file_dependencies: diffusion_distributed_attention
         commands:
           - timeout 20m pytest -sv tests/diffusion/distributed -m 'core_model and cuda and L4 and cards_2' --run-level "core_model"
         mirror_hardwares: l4_2
 
       - label: "Diffusion · Distributed & Attention Test · 4-GPU"
+        source_file_dependencies: diffusion_distributed_attention
         commands:
           - timeout 20m pytest -sv tests/diffusion/distributed -m 'core_model and cuda and L4 and cards_4' --run-level "core_model"
           - timeout 20m pytest -sv tests/diffusion/attention/test_attention_sp.py -m 'core_model and cuda and L4 and cards_4' --run-level "core_model"
@@ -120,29 +123,14 @@ steps:
     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/
+        source_file_dependencies: custom_pipeline
         commands:
           - timeout 20m pytest -s -v tests/e2e/features/custom_pipeline/ -m "core_model"
         mirror_hardwares: l4_1
 
 
       - 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/
+        source_file_dependencies: rlhf_verl_omni
         commands:
           - |
             timeout 20m bash -c "
@@ -151,17 +139,7 @@ steps:
         mirror_hardwares: l4_1
 
       - label: "Omni · Qwen3-Omni Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen3_omni.py
-          - tests/helpers/runtime.py
-          - vllm_omni/entrypoints/openai/serving_chat.py
-          - vllm_omni/model_executor/models/qwen3_omni/
-          - vllm_omni/model_executor/models/common/qwen3_code_predictor.py
-          - vllm_omni/model_executor/models/common/snake_activation.py
-          - vllm_omni/model_executor/models/qwen2_5_omni/qwen2_5_omni_thinker.py
-          - vllm_omni/model_executor/models/qwen3_tts/cuda_graph_decoder_wrapper.py
-          - vllm_omni/model_executor/stage_input_processors/qwen3_omni.py
-          - vllm_omni/deploy/qwen3_omni_moe.yaml
+        source_file_dependencies: omni_qwen3_omni_function
         commands:
           - |
             timeout 20m bash -c "
@@ -170,14 +148,7 @@ steps:
         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/model_executor/models/minicpmo_4_5/
-          - vllm_omni/model_executor/models/step_audio2/
-          - vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
-          - vllm_omni/model_executor/models/cosyvoice3/utils.py
-          - vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
-          - vllm_omni/deploy/minicpmo_4_5.yaml
+        source_file_dependencies: omni_minicpmo_4_5_function
         commands:
           - |
             timeout 20m bash -c "
@@ -186,15 +157,7 @@ steps:
         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/transformers_utils/chat_templates/minicpmo45_native.jinja
-          - vllm_omni/model_executor/models/minicpmo_4_5/
-          - vllm_omni/model_executor/models/step_audio2/
-          - vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
-          - vllm_omni/model_executor/models/cosyvoice3/utils.py
-          - vllm_omni/model_executor/stage_input_processors/minicpmo_4_5_omni.py
-          - vllm_omni/deploy/minicpmo_4_5.yaml
+        source_file_dependencies: omni_minicpmo_4_5_function
         commands:
           - |
             timeout 20m bash -c "
@@ -203,48 +166,7 @@ steps:
         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_server_vad.py
-          - tests/e2e/online_serving/run_minicpmo_realtime_duplex_soft_interrupt.py
-          - vllm_omni/deploy/minicpmo_4_5.yaml
-          - tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py
-          - vllm_omni/engine/duplex/
-          - vllm_omni/entrypoints/duplex/
-          # Public duplex client library + its unit suites: client-side
-          # changes must re-run the duplex e2e group, which includes the
-          # live client probe (test_duplex_client_live.py, single GPU).
-          - vllm_omni/clients/
-          - tests/clients/
-          - tests/e2e/online_serving/test_duplex_client_live.py
-          - vllm_omni/entrypoints/duplex_request_client.py
-          - vllm_omni/outputs/duplex.py
-          - vllm_omni/model_executor/duplex_sampling.py
-          - tests/engine/duplex/
-          - tests/entrypoints/duplex/
-          - tests/model_executor/models/minicpmo_4_5/duplex/
-          # Legacy Realtime probe client + video stacking used by the e2e drivers.
-          - vllm_omni/experimental/fullduplex/
-          - vllm_omni/model_executor/models/minicpmo_4_5/
-          - vllm_omni/model_executor/models/step_audio2/
-          - vllm_omni/model_executor/models/cosyvoice3/code2wav_core/
-          - vllm_omni/model_executor/models/cosyvoice3/utils.py
-          - 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/engine/orchestrator.py
-          - vllm_omni/entrypoints/cli/serve.py
-          - vllm_omni/entrypoints/openai/api_server.py
-          - vllm_omni/entrypoints/openai/duplex_capability.py
-          - vllm_omni/config/stage_config.py
+        source_file_dependencies: omni_minicpmo_4_5_duplex_function
         commands:
           - |
             timeout 35m bash -c "
@@ -254,29 +176,14 @@ steps:
 
       - 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
+        source_file_dependencies: omni_minicpmo_4_5_perf
         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 · Qwen3-TTS CustomVoice Test"
-        source_file_dependencies:
-          - tests/helpers/media.py
-          - tests/e2e/online_serving/test_qwen3_tts_customvoice.py
-          - vllm_omni/model_executor/models/qwen3_tts/
-          - vllm_omni/model_executor/models/common/qwen3_code_predictor.py
-          - vllm_omni/model_executor/models/common/snake_activation.py
-          - vllm_omni/model_executor/models/common/alias_free_activation.py
-          - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
-          - vllm_omni/deploy/qwen3_tts.yaml
-          - vllm_omni/entrypoints/openai/serving_speech.py
-          - vllm_omni/entrypoints/openai/tts_adapters/
-          - vllm_omni/engine/stage_pool.py
+        source_file_dependencies: tts_qwen3_tts_function
         commands:
           - |
             timeout 20m bash -c "
@@ -286,10 +193,7 @@ steps:
         mirror_hardwares: l4_1
 
       - label: "Diffusion · Wan22 Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_wan22_t2v.py
-          - vllm_omni/diffusion/models/wan2_2/
-          - vllm_omni/diffusion/models/dmd2/
+        source_file_dependencies: diffusion_wan22_function
         commands:
           - |
             timeout 40m bash -c "
@@ -299,12 +203,7 @@ steps:
         mirror_hardwares: h100_1
 
       - label: "Diffusion · Cosmos3 Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_cosmos3.py
-          - vllm_omni/diffusion/models/cosmos3/
-          - vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_wan.py
-          - vllm_omni/experimental/world_models/
-          - vllm_omni/model_extras/cosmos3.py
+        source_file_dependencies: diffusion_cosmos3_function
         commands:
           - |
             timeout 40m bash -c "
@@ -315,14 +214,7 @@ steps:
 
       - label: "Diffusion · MiniMax-H3 DLO DP2 T2VA Test"
         timeout_in_minutes: 90
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_minimax_h3_dlo_dp2_t2va.py
-          - tests/helpers/assertions.py
-          - tests/helpers/runtime.py
-          - vllm_omni/diffusion/models/minimax_h3/
-          - vllm_omni/diffusion/offloader/
-          - vllm_omni/diffusion/distributed/
-          - vllm_omni/entrypoints/openai/
+        source_file_dependencies: diffusion_minimax_h3_function
         commands:
           - |
             timeout 80m bash -c "
@@ -332,11 +224,7 @@ steps:
         mirror_hardwares: h100_2
 
       - label: "Diffusion · Qwen Image Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen_image.py
-          - vllm_omni/diffusion/models/qwen_image/
-          - vllm_omni/diffusion/models/dmd2/
-          - vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_qwenimage.py
+        source_file_dependencies: diffusion_qwen_image_function
         commands:
           - |
             timeout 40m bash -c "
@@ -346,9 +234,7 @@ steps:
         mirror_hardwares: h100_1
 
       - label: "Diffusion · HunyuanVideo-1.5 Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_hunyuan_video_15_expansion.py
-          - vllm_omni/diffusion/models/hunyuan_video/
+        source_file_dependencies: diffusion_hunyuan_video_function
         commands:
           - |
             timeout 40m bash -c "

.buildkite/cuda/test-weekly.yml

@@ -29,36 +29,42 @@ steps:
     steps:
 
       - label: "Reliability Test · qwen3-omni"
+        source_file_dependencies: omni_qwen3_omni_reliability
         timeout_in_minutes: 180
         commands:
           - pytest -s -v tests/dfx/reliability/test_reliability_qwen3_omni.py -m "slow"
         mirror_hardwares: h100_2
 
       - label: "Reliability Test · wan22"
+        source_file_dependencies: diffusion_wan22_reliability
         timeout_in_minutes: 180
         commands:
           - pytest -s -v tests/dfx/reliability/test_reliability_wan22.py -m "slow"
         mirror_hardwares: h100_2
 
       - label: "Reliability Test · hunyuan-image"
+        source_file_dependencies: diffusion_hunyuan_image3_reliability
         timeout_in_minutes: 180
         commands:
           - pytest -s -v tests/dfx/reliability/test_reliability_hunyuan_image.py -m "slow"
         mirror_hardwares: h100_4
 
       - label: "Reliability Test · Invalid parameters · H100 · Single-GPU"
+        source_file_dependencies: reliability_invalid_param_h100
         timeout_in_minutes: 90
         commands:
           - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and H100 and cards_1"
         mirror_hardwares: h100_1
 
       - label: "Reliability Test · Invalid parameters · H100 · 2-GPU"
+        source_file_dependencies: reliability_invalid_param_h100
         timeout_in_minutes: 90
         commands:
           - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and H100 and cards_2"
         mirror_hardwares: h100_2
 
       - label: "Reliability Test · Invalid parameters · L4"
+        source_file_dependencies: reliability_invalid_param_l4
         timeout_in_minutes: 120
         commands:
           - pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and L4"
@@ -70,6 +76,7 @@ steps:
     steps:
 
       - label: ":full_moon: Omni · Perf Test · vLLM Text"
+        source_file_dependencies: omni_qwen3_omni_perf
         key: weekly-omni-performance-vllm-text
         timeout_in_minutes: 180
         commands:
@@ -96,6 +103,7 @@ steps:
         mirror_hardwares: h100_2
 
       - label: ":full_moon: Omni · Perf Test · Multi-Replica"
+        source_file_dependencies: omni_qwen3_omni_perf
         key: weekly-omni-performance-multi-replicas
         timeout_in_minutes: 180
         commands:
@@ -221,21 +229,262 @@ steps:
             --run-level "full_model"
         mirror_hardwares: l4_4
 
-      - label: "Diffusion · H100 · Single-GPU"
-        timeout_in_minutes: 150
+      # Split the old shared H100 Single-GPU sweep: one pytest process collected
+      # every slow+cards_1 diffusion file and exceeded 150 minutes.
+      - label: "Diffusion · Qwen-Image · H100 · Single-GPU"
+        timeout_in_minutes: 120
         commands:
           - >-
             pytest -sv
-            tests/e2e/ -m "slow and diffusion and H100 and cards_1"
+            tests/e2e/online_serving/test_qwen_image_edit.py
+            tests/e2e/online_serving/test_qwen_image_edit_expansion.py
+            tests/e2e/online_serving/test_qwen_image_layered.py
+            tests/e2e/online_serving/test_qwen_image_layered_expansion.py
+            tests/e2e/accuracy/test_qwen_image_edit.py
+            tests/e2e/accuracy/test_qwen_image_layered.py
+            -m "slow and diffusion and H100 and cards_1"
             --run-level "full_model"
         mirror_hardwares: h100_1
 
-      - label: "Diffusion · H100 · 2-GPU"
+      - label: "Diffusion · Wan2.1 VACE · H100 · Single-GPU"
         timeout_in_minutes: 90
         commands:
           - >-
             pytest -sv
-            tests/e2e/ -m "slow and diffusion and H100 and cards_2"
+            tests/e2e/online_serving/test_wan_2_1_vace_expansion.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · LongCat · H100 · Single-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_longcat_image_expansion.py
+            tests/e2e/online_serving/test_longcat_image_edit_expansion.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · Bagel · H100 · Single-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_bagel.py
+            tests/e2e/online_serving/test_bagel_expansion.py
+            tests/e2e/offline_inference/test_bagel.py
+            tests/e2e/offline_inference/test_bagel_expansion.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · Boogu · H100 · Single-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            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
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · Flux · H100 · Single-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_flux_2_dev_expansion.py
+            tests/e2e/offline_inference/test_flux1_schnell_expansion.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · LTX · H100 · Single-GPU"
+        timeout_in_minutes: 120
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_ltx.py
+            tests/e2e/online_serving/test_ltx25.py
+            tests/e2e/accuracy/ltx/test_ltx_official_similarity.py
+            tests/e2e/accuracy/ltx/test_ltx25_official_similarity.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · Krea2 · H100 · Single-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_krea2_expansion.py
+            tests/e2e/offline_inference/test_krea2_expansion.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · HiDream-I1 · H100 · Single-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_hidream_i1_full_expansion.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · SANA-Video · H100 · Single-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_sana_video_expansion.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · SenseNova-U1 · H100 · Single-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/offline_inference/test_sensenova_u1_expansion.py
+            tests/e2e/offline_inference/test_sensenova_u1_text2img_expansion.py
+            tests/e2e/offline_inference/test_sensenova_u1_img2img_expansion.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · MammothModa2 · H100 · Single-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/offline_inference/test_mammoth_moda2_expansion.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      - label: "Diffusion · Helios · H100 · Single-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/accuracy/test_video_streaming_output_similarity.py
+            -m "slow and diffusion and H100 and cards_1"
+            --run-level "full_model"
+        mirror_hardwares: h100_1
+
+      # Split the old shared H100 2-GPU sweep: one pytest process collected every
+      # slow+cards_2 diffusion file and exceeded 90 minutes.
+      - label: "Diffusion · Qwen-Image · H100 · 2-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_qwen_image_edit_expansion.py
+            tests/e2e/online_serving/test_qwen_image_layered_expansion.py
+            -m "slow and diffusion and H100 and cards_2"
+            --run-level "full_model"
+        mirror_hardwares: h100_2
+
+      - label: "Diffusion · Wan2.1 VACE · H100 · 2-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_wan_2_1_vace_expansion.py
+            -m "slow and diffusion and H100 and cards_2"
+            --run-level "full_model"
+        mirror_hardwares: h100_2
+
+      - label: "Diffusion · LongCat · H100 · 2-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_longcat_image_expansion.py
+            tests/e2e/online_serving/test_longcat_image_edit_expansion.py
+            -m "slow and diffusion and H100 and cards_2"
+            --run-level "full_model"
+        mirror_hardwares: h100_2
+
+      - label: "Diffusion · Bagel · H100 · 2-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_bagel_expansion.py
+            -m "slow and diffusion and H100 and cards_2"
+            --run-level "full_model"
+        mirror_hardwares: h100_2
+
+      - label: "Diffusion · Boogu · H100 · 2-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_boogu_image_expansion.py
+            tests/e2e/online_serving/test_boogu_image_edit_expansion.py
+            -m "slow and diffusion and H100 and cards_2"
+            --run-level "full_model"
+        mirror_hardwares: h100_2
+
+      - label: "Diffusion · Flux · H100 · 2-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_flux_2_dev_expansion.py
+            tests/e2e/offline_inference/test_flux1_kontext_expansion.py
+            -m "slow and diffusion and H100 and cards_2"
+            --run-level "full_model"
+        mirror_hardwares: h100_2
+
+      - label: "Diffusion · GLM-Image · H100 · 2-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_glm_image_expansion.py
+            tests/e2e/offline_inference/test_glm_image_autoround_w4a16_expansion.py
+            -m "slow and diffusion and H100 and cards_2"
+            --run-level "full_model"
+        mirror_hardwares: h100_2
+
+      - label: "Diffusion · LTX · H100 · 2-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_ltx.py
+            -m "slow and diffusion and H100 and cards_2"
+            --run-level "full_model"
+        mirror_hardwares: h100_2
+
+      - label: "Diffusion · Krea2 · H100 · 2-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/offline_inference/test_krea2_expansion.py
+            -m "slow and diffusion and H100 and cards_2"
+            --run-level "full_model"
+        mirror_hardwares: h100_2
+
+      - label: "Diffusion · DreamZero · H100 · 2-GPU"
+        timeout_in_minutes: 90
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_dreamzero_expansion.py
+            tests/e2e/accuracy/test_dreamzero.py
+            -m "slow and diffusion and H100 and cards_2"
             --run-level "full_model"
         mirror_hardwares: h100_2
 
@@ -246,4 +495,33 @@ steps:
             pytest -sv
             tests/e2e/ -m "slow and diffusion and H100 and cards_4"
             --run-level "full_model"
+            --ignore=tests/e2e/online_serving/test_magi2.py
+        mirror_hardwares: h100_4
+
+      # Dedicated: HiDream-O1 accuracy needs a long TP2 run; the shared H100
+      # 2-GPU sweep is only 90 minutes.
+      - label: "Diffusion · HiDream-O1-Image Accuracy · H100 · 2-GPU"
+        timeout_in_minutes: 180
+        commands:
+          - pytest -s -v tests/e2e/accuracy/test_hidream_o1_image.py -m "slow and diffusion and cuda and H100 and cards_2" --run-level "full_model"
+        mirror_hardwares: h100_2
+
+      # Dedicated: Boogu CFG-parallel size 3 needs 3 GPUs; weekly has no H100 3-GPU sweep.
+      - label: "Diffusion · Boogu Edit CFG · H100 · 3-GPU"
+        timeout_in_minutes: 120
+        commands:
+          - >-
+            pytest -sv
+            tests/e2e/online_serving/test_boogu_image_edit_expansion.py
+            -k "test_double_guidance_cfg_parallel and cfg_parallel_3_full"
+            -m "slow and diffusion and cuda and H100 and cards_3"
+            --run-level "full_model"
+        mirror_hardwares: h100_3
+
+      # Dedicated: MAGI-2 Preview serving smoke needs ~30 min server init; the
+      # shared H100 4-GPU sweep is only 90 minutes.
+      - label: "Diffusion · MAGI-2 Preview Serving Smoke · H100 · 4-GPU"
+        timeout_in_minutes: 180
+        commands:
+          - pytest -s -v tests/e2e/online_serving/test_magi2.py -m "slow and diffusion and cuda and H100 and cards_4" --run-level "full_model"
         mirror_hardwares: h100_4

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

@@ -93,7 +93,7 @@ steps:
     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)
+  # L4 Test — main+NIGHTLY=1 (scheduled), or PR nightly-test label
   - label: "Upload Nightly Pipeline"
     depends_on:
       - image-build-a2
@@ -102,6 +102,11 @@ steps:
       - image-build-310p
     key: upload-nightly-pipeline
     commands:
-      - python3 .buildkite/common/scripts/upload_pipeline.py --upload .buildkite/npu/test-npu-nightly.yml
+      - |
+        EXTRA=""
+        if [ "${NIGHTLY:-}" = "1" ] && [ "${BUILDKITE_BRANCH}" = "main" ]; then
+          EXTRA="--all"
+        fi
+        python3 .buildkite/common/scripts/upload_pipeline.py --upload $$EXTRA .buildkite/npu/test-npu-nightly.yml
     agents:
       queue: "cpu_queue_premerge"

.buildkite/npu/pipeline-npu-a3.yml

@@ -96,13 +96,7 @@
   #   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"
-  #     ))
+  #     (build.branch != "main" && build.pull_request.labels includes "nightly-test")
   #   commands:
   #     - buildkite-agent pipeline upload .buildkite/npu/test-npu-nightly.yml
   #   agents:

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

@@ -4,10 +4,10 @@ steps:
     depends_on: upload-nightly-pipeline
     if: >-
       build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test" ||
-      build.pull_request.labels includes "omni-test"
+      build.pull_request.labels includes "nightly-test"
     steps:
       - label: ":full_moon: Omni · Perf Test · No Async Chunk"
+        source_file_dependencies: omni_qwen3_omni_perf
         key: nightly-omni-performance-no-async-chunk
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_4
@@ -24,6 +24,7 @@ steps:
             buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
             exit $$EXIT
       - label: ":full_moon: Omni · Perf Test · Async Chunk"
+        source_file_dependencies: omni_qwen3_omni_perf
         key: nightly-omni-performance-async-chunk
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_4
@@ -40,6 +41,7 @@ steps:
             buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
             exit $$EXIT
       - label: ":full_moon: Omni · MiniCPM-o 4.5 Test"
+        source_file_dependencies: omni_minicpmo_4_5_function
         mirror_hardwares: a3_npu_2
         env:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
@@ -48,6 +50,7 @@ steps:
         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"
+        source_file_dependencies: omni_minicpmo_4_5_duplex_function
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_2
         env:
@@ -62,6 +65,7 @@ steps:
             -m "npu and A3 and omni"
             --run-level full_model
       - label: ":full_moon: Omni · MiniCPM-o 4.5 · Accuracy Test"
+        source_file_dependencies: omni_minicpmo_4_5_accuracy
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_2
         env:
@@ -82,6 +86,7 @@ steps:
             buildkite-agent artifact upload "tests/e2e/accuracy/minicpmo_4_5/results/*.json"
             exit $$EXIT
       - label: ":full_moon: Omni · MiniCPM-o 4.5 · Perf Test"
+        source_file_dependencies: omni_minicpmo_4_5_perf
         key: nightly-omni-performance-minicpmo-4-5-npu
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_2
@@ -98,6 +103,7 @@ steps:
             buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
             exit $$EXIT
       - label: ":full_moon: Omni · MiniCPM-o 4.5 · Perf Test (A2)"
+        source_file_dependencies: omni_minicpmo_4_5_perf
         key: nightly-omni-performance-minicpmo-4-5-npu-a2
         timeout_in_minutes: 180
         mirror_hardwares: a2b3_npu_1
@@ -115,6 +121,7 @@ steps:
             buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
             exit $$EXIT
       - label: ":full_moon: Omni · MiniCPM-o 4.5 · Duplex Seed-TTS Perf Test"
+        source_file_dependencies: omni_minicpmo_4_5_duplex_perf
         key: nightly-omni-performance-minicpmo-4-5-duplex-seed-tts-npu
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_2
@@ -133,9 +140,10 @@ steps:
   - group: ":card_index_dividers: TTS Model Test"
     key: nightly-tts-test-group
     depends_on: upload-nightly-pipeline
-    if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test" || build.pull_request.labels includes "tts-test"
+    if: build.env("NIGHTLY") == "1" || build.pull_request.labels includes "nightly-test"
     steps:
       - label: ":full_moon: TTS · Perf Test"
+        source_file_dependencies: tts_qwen3_tts_perf
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_2
         env:
@@ -151,15 +159,15 @@ steps:
             EXIT=$$?
             buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
             exit $$EXIT
-  - group: ":card_index_dividers: Diffusion I2I Model Test"
-    key: nightly-HunyuanImage3-x2i-test-group
+  - group: ":card_index_dividers: Diffusion X2I(&A&T) Model Test"
+    key: nightly-diffusion-x2iat-group
     depends_on: upload-nightly-pipeline
     if: >-
       build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test" ||
-      build.pull_request.labels includes "diffusion-x2iat-test"
+      build.pull_request.labels includes "nightly-test"
     steps:
       - label: ":full_moon: HunyuanImage3-DIT · Accuracy Test"
+        source_file_dependencies: diffusion_hunyuan_image3_accuracy
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_4
         env:
@@ -169,15 +177,8 @@ steps:
           DIFFUSION_ATTENTION_BACKEND: TORCH_SDPA
         commands:
           - pytest -s -v tests/e2e/accuracy/test_hunyuan_image3_pixel_accuracy.py -m "full_model and A3" --run-level full_model
-  - group: ":card_index_dividers: Diffusion Benchmark Perf Test"
-    key: nightly-diffusion-benchmark-group
-    depends_on: upload-nightly-pipeline
-    if: >-
-      build.env("NIGHTLY") == "1" ||
-      build.pull_request.labels includes "nightly-test" ||
-      build.pull_request.labels includes "diffusion-x2iat-test"
-    steps:
       - label: ":full_moon: Diffusion Perf · HunyuanImage3 TP=2 CFGP=2"
+        source_file_dependencies: diffusion_hunyuan_image3_perf
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_4
         env:
@@ -194,6 +195,7 @@ steps:
             buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
             exit $$EXIT
       - label: ":full_moon: Diffusion Perf · HunyuanImage3 TP=2 SP=2"
+        source_file_dependencies: diffusion_hunyuan_image3_perf
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_4
         env:
@@ -210,6 +212,7 @@ steps:
             buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
             exit $$EXIT
       - label: ":full_moon: Diffusion Perf · HunyuanImage3 TP=4"
+        source_file_dependencies: diffusion_hunyuan_image3_perf
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_4
         env:
@@ -230,10 +233,10 @@ steps:
     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"
+      build.pull_request.labels includes "nightly-test"
     steps:
-      - label: ":full_moon: Diffusion X2V · Function Test"
+      - label: ":full_moon: Diffusion X2V · Wan 2.2 Function Test"
+        source_file_dependencies: diffusion_wan22_function
         mirror_hardwares: a2b3_npu_4
         env:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
@@ -241,7 +244,8 @@ steps:
           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"
+      - label: ":full_moon: Diffusion X2V · Wan 2.2 Perf Test"
+        source_file_dependencies: diffusion_wan22_perf
         key: nightly-diffusion-x2v-performance
         timeout_in_minutes: 180
         mirror_hardwares: a3_npu_4

.claude/skills/vllm-omni-test/SKILL.md

@@ -468,10 +468,10 @@ When the user asks for **invalid parameter validation**, **invalid request bodie
 | **Invalid parameters Test · H100** | `pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and H100"` | Diffusion / omni / video invalid-param tests with `H100` hardware mark |
 | **Invalid parameters Test · L4** | `pytest -s -v tests/dfx/reliability/invalid_param_test/ -m "slow and L4"` | TTS / lighter models marked `L4` |
 
-- **Trigger:** `build.env("WEEKLY") == "1"` or PR label `weekly-test`.
+- **Trigger:** `build.env("WEEKLY") == "1"` (all weekly jobs) or PR label `weekly-test` (Reliability / Perf, then filtered by `source_file_dependencies`).
 - **Default:** extending an existing `invalid_param_test` script needs **no YAML edit** — the weekly steps already sweep the whole directory.
 - **Edit YAML only** when adding a **new hardware queue**, a **new top-level script** that must run in isolation, or a **model-specific weekly shard** (mirror neighboring reliability steps).
-- Weekly steps **do not** use `source_file_dependencies`.
+- Weekly Reliability / Perf jobs declare `source_file_dependencies`. Filtering applies only on the `weekly-test` label; `WEEKLY=1` on `main` keeps every job in those groups. CPU coverage (`WEEKLY=1` only) and the E2E Tests group (`NON_CRITICAL=1` only) do **not** use this field.
 
 **Example — append to `test_invalid_image_generation.py`:**
 
@@ -644,7 +644,7 @@ If the test is not already collected by an existing pipeline command (for exampl
 | **L2** | `test-ready.yml` with `core_model` + `source_file_dependencies` | merge / nightly pipelines |
 | **Invalid param** | `test-weekly.yml` — **Invalid parameters Test** group (`-m "slow and H100"` / `-m "slow and L4"`). Usually **no YAML edit** when appending cases to existing `invalid_param_test` scripts | `test-ready.yml`, `test-merge.yml`, `test-nightly.yml` |
 
-`test-nightly.yml` shards use **explicit pytest file paths** in `commands` (and PR labels like `diffusion-x2iat-test`); they generally **do not** use `source_file_dependencies`. Only suggest merge/ready YAML when the requested level is L3/L2 (or the user explicitly asks for multi-level CI).
+`test-nightly.yml` shards use **explicit pytest file paths** in `commands` plus `source_file_dependencies`; PR trigger is `nightly-test` (path filter), or `NIGHTLY=1` on `main` (all jobs). Only suggest merge/ready YAML when the requested level is L3/L2 (or the user explicitly asks for multi-level CI).
 
 **`test-nightly.yml` top-level groups** (each uses `full_model` + type marker in pytest `-m`):
 
@@ -653,7 +653,7 @@ If the test is not already collected by an existing pipeline command (for exampl
 | **Omni Model Test** | `omni` | Function / doc / accuracy / **perf** for Qwen-Omni family |
 | **TTS Model Test** | `tts` | `-m "full_model and L4 and tts"` (and H100 variants when enabled); **Perf Test** uses `run_benchmark.py` + `test_tts.json` |
 | **Diffusion X2I(&A&T) Model Test** | `diffusion` | Image/audio/text diffusion; explicit file shards for **Function**; **Perf Test · <Model>** uses `run_diffusion_benchmark.py` + JSON config |
-| **Diffusion X2V Model Test** | `diffusion` | Video-only (Wan, HunyuanVideo, …); PR label `diffusion-x2v-test`; separate **Perf** steps when in-tree |
+| **Diffusion X2V Model Test** | `diffusion` | Video-only (Wan, HunyuanVideo, …); separate **Perf** steps when in-tree |
 
 Guidelines when editing YAML:
 

.claude/skills/vllm-omni-test/references/test-routing.md

@@ -37,7 +37,7 @@ Every model-centric e2e test must declare **exactly one** type marker:
 | **Diffusion X2I(&A&T) Model Test** | x2**i** / x2**a** / x2**t** — image, audio, text (non-video) | Qwen-Image*, BAGEL, FLUX, SD3, Z-Image, LongCat, DreamZero |
 | **Diffusion X2V Model Test** | x2**v** — video only | Wan2.2, HunyuanVideo 1.5, Wan VACE |
 
-PR labels for selective nightly runs: `diffusion-x2iat-test`, `diffusion-x2v-test` (plus `nightly-test` / `NIGHTLY=1`).
+PR label for L4 on a branch: `nightly-test` (jobs then filtered by `source_file_dependencies`). Scheduled `main` uses `NIGHTLY=1` and runs every nightly job. L5 Reliability / Perf use `weekly-test` with the same path filter; CPU coverage and the weekly E2E group are env-only (`WEEKLY=1` / `NON_CRITICAL=1`) and are not source-filtered.
 
 ## Level and Marker Mapping
 
@@ -238,7 +238,7 @@ pytest -s -v dfx/reliability/invalid_param_test/ -m "slow and L4"
 pytest -s -v dfx/reliability/invalid_param_test/test_invalid_image_generation.py::test_images_generations_invalid_requests -m "slow and H100"
 ```
 
-**Trigger:** `WEEKLY=1` or PR label `weekly-test`. Appending cases to existing scripts usually needs **no YAML edit** (directory sweep). No `source_file_dependencies` on weekly steps.
+**Trigger:** `WEEKLY=1` (all jobs) or PR label `weekly-test` (Reliability / Perf, filtered by `source_file_dependencies`). Appending cases to existing scripts usually needs **no YAML edit** (directory sweep).
 
 ### Platform-targeted examples
 

docs/contributing/ci/ci_settings.md

@@ -15,7 +15,8 @@ Canonical layout (prefer these paths for new changes):
 │   │   ├── skip_ci.py               # skip-ci decision (docs / skip-mark / CI YAML paths)
 │   │   ├── upload_pipeline.py       # Bootstrap + test-pipeline uploader (CUDA/NPU)
 │   │   └── resolve_skip_ci.sh       # Shell helpers for AMD/Intel bootstrap
-│   └── ci_mirror_hardwares.yml      # CUDA uploader presets (referenced by name only)
+│   ├── ci_mirror_hardwares.yml      # CUDA/NPU hardware presets (referenced by name only)
+│   └── ci_source_file_dependencies.yml  # L2–L5 path-prefix presets (referenced by name only)
 ├── cuda/                            # Primary NVIDIA CUDA CI
 │   ├── pipeline.yml                 # Bootstrap entry (hook upload)
 │   ├── bootstrap-upload-steps.yml   # Bootstrap child steps (upload_pipeline --upload)
@@ -108,19 +109,21 @@ Canonical layout (prefer these paths for new changes):
 
     Inferred form: unset/`empty` `MIRROR_HW` matches `H100` or `L4` in `-m` (both present → H100); no match skips the step. `MIRROR_HW=b200` must appear in `-m` or the step is skipped. The uploader does **not** rewrite pytest `-m`; B200 collection comes from the YAML expression and from tests that declare `B200` in `hardware_test` / `hardware_marks` (for example `res={"cuda": ["H100", "B200"]}`). `MIRROR_HW` must be empty or `b200` (case-insensitive); unknown values (for example `b20o`) **fail the upload**. A CUDA preset string such as `mirror_hardwares: h100_4` is skipped when `MIRROR_HW=b200`. Unset `MIRROR_HW` keeps string presets. NPU presets ignore `MIRROR_HW`. A `mirror_hardwares` name that is not a key in `ci_mirror_hardwares.yml` **fails the upload**.
 
+    **Path filter in YAML:** `source_file_dependencies: <preset>` (string, or a list of preset names)—preset names in [`common/ci_source_file_dependencies.yml`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/common/ci_source_file_dependencies.yml). Required on **E2E Test** leaf jobs in L2/L3, and on L4/L5 leaf jobs that should be diff-gated on PR labels; see [Step filtering](#step-filtering).
+
     **Conventions**
 
     - **`depends_on`:** leaf jobs depend on `upload-ready-pipeline`, `upload-merge-pipeline`, etc.
     - **`group` / `label`:** `:card_index_dividers:` groups; labels like `Diffusion · Qwen Image Test`.
     - **`commands`:** `timeout … pytest …` with markers and `--run-level` for the pipeline level.
-    - **`source_file_dependencies`:** required on **E2E Test** leaf jobs in L2/L3; see [Step filtering](#step-filtering).
+    - **`source_file_dependencies`:** required on **E2E Test** leaf jobs in L2/L3, and on L4/L5 leaf jobs that should be diff-gated on PR labels; name a job key from `ci_source_file_dependencies.yml` (see [Step filtering](#step-filtering)). The key must list every script the step runs; `commands` is not scanned.
 
     **Adding a job**
 
     1. Pick the level file (`test-ready.yml` / `test-merge.yml` / `test-nightly.yml` / `test-weekly.yml`).
     2. Add a step under the right **group** (usually **E2E Test** for model pytest).
-    3. Set `label`, `commands`, `mirror_hardwares`, `depends_on: upload-ready-pipeline` (or `upload-merge-pipeline` / `upload-nightly-pipeline` / `upload-weekly-pipeline`).
-    4. For L2/L3 E2E, add `source_file_dependencies` (pytest + model + deploy YAML prefixes).
+    3. Set `label`, `commands`, `mirror_hardwares`, `depends_on: upload-<level>-pipeline`.
+    4. For L2–L5 jobs that should be diff-gated, add a job key in `common/ci_source_file_dependencies.yml` and set `source_file_dependencies: <key>` on the step. YAML anchors hold model business-code paths only. The job key (`{model}_function` / `_perf` / `_accuracy` / `_reliability` / `_doc` / `_cov`) aliases that anchor and lists the pytest / example / benchmark scripts the step actually runs. The uploader does **not** parse `commands` for path filters—omitting a script from the key means editing that script will not select the job.
     5. Dry-run:
 
     ```bash
@@ -144,6 +147,8 @@ Canonical layout (prefer these paths for new changes):
     - A5: `a5_npu_2`, `a5_npu_4`, `a5_npu_8`, `a5_npu_16`
     - 310P: `310p_npu_1`, `310p_npu_2`, `310p_npu_4`
 
+    **Path filter in YAML:** same `source_file_dependencies` presets as CUDA, on **L4** leaf jobs in `test-npu-nightly.yml`. Filtering applies on the PR `nightly-test` label; `main` + `NIGHTLY=1` keeps every job. If no job-key prefix matches, a change to the pipeline YAML being uploaded, or to any path under `source_filter_fallback`, keeps every job in that upload. See [Step filtering](#step-filtering).
+
     **Conventions**
 
     - **`depends_on: upload-ready-pipeline`** (or `upload-nightly-pipeline`) ties jobs to bootstrap upload keys.
@@ -153,7 +158,7 @@ Canonical layout (prefer these paths for new changes):
 
     1. Edit `test-npu-ready.yml` (L2) or `test-npu-nightly.yml` (L4).
     2. Add a step with `mirror_hardwares` (add a new preset in `ci_mirror_hardwares.yml` first if needed).
-    3. Set `commands` to your pytest file and markers.
+    3. Set `commands` to your pytest file and markers. For L4, set `source_file_dependencies` to a job key from `ci_source_file_dependencies.yml` that aliases the model anchor and lists that pytest file.
     4. Dry-run:
 
     ```bash
@@ -213,7 +218,7 @@ PR diffs drive **two independent skip layers**. Both read changed files from git
 | Layer | Script | When | What is skipped | Where you configure |
 | ----- | ------ | ---- | --------------- | ------------------- |
 | **Bootstrap** | [`skip_ci.py`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/common/scripts/skip_ci.py) + [`upload_pipeline.py`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/common/scripts/upload_pipeline.py) | Before child test pipelines upload (`cuda/pipeline.yml`, `npu/pipeline-npu.yml`, AMD/Intel bootstraps) | Entire default CI, or whole L2/L3 upload for a platform | Whitelists in `skip_ci.py`; bootstrap `if` injected by step `key` in `upload_pipeline.py` |
-| **Step filter** | [`upload_pipeline.py`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/common/scripts/upload_pipeline.py) | While uploading CUDA L2/L3 YAML | Individual Buildkite steps inside `test-ready.yml` / `test-merge.yml` | `source_file_dependencies` on each step or group |
+| **Step filter** | [`upload_pipeline.py`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/common/scripts/upload_pipeline.py) | While uploading CUDA L2–L5 YAML | Individual Buildkite steps inside `test-ready.yml` / `test-merge.yml` / `test-nightly.yml` / `test-weekly.yml` | `source_file_dependencies` key on each step (presets in `ci_source_file_dependencies.yml`) |
 
 **Changed files** (both layers):
 
@@ -306,40 +311,38 @@ Unit coverage: `tests/buildkite/test_skip_ci.py`.
 
 #### Step filtering {#step-filtering}
 
-CUDA **L2** (`.buildkite/cuda/test-ready.yml`) and **L3** (`.buildkite/cuda/test-merge.yml`) only. Bootstrap upload entry: `upload_pipeline.py --upload .buildkite/cuda/bootstrap-upload-steps.yml`.
+CUDA **L2** (`.buildkite/cuda/test-ready.yml`), **L3** (`.buildkite/cuda/test-merge.yml`), **L4** (`.buildkite/cuda/test-nightly.yml`), **L5** (`.buildkite/cuda/test-weekly.yml`), and NPU **L4** (`.buildkite/npu/test-npu-nightly.yml`). Bootstrap upload entry: `upload_pipeline.py --upload .buildkite/cuda/bootstrap-upload-steps.yml` (or `npu/bootstrap-upload-steps.yml`).
+
+**When filtering applies:** only **PR label** uploads (`ready`, `merge-test`, `nightly-test`, `weekly-test`). On **`main` + env** (`NIGHTLY=1`, post-merge L3, `WEEKLY=1` / `NON_CRITICAL=1`, `WEEKLY=1 --e2e`) the uploader keeps every job and still strips the key. If **no** job-key prefix matches the diff, a change to the pipeline YAML being uploaded, or any path under the `source_filter_fallback` key in `ci_source_file_dependencies.yml`, keeps every job in that upload. `source_filter_fallback` is not a job key — do not attach it to a step. When any job-key prefix already matches, normal filtering wins (the fallback does not expand the selection). Without this fallback, command / env / hardware-only edits would match nothing (NPU drops every step; CUDA nightly keeps only the email aggregator). A different pipeline YAML does not trigger the fallback for this upload.
 
 **Uploader-only keys** — removed before Buildkite sees the YAML; never used at runtime on agents:
 
 | Key | Purpose |
 | --- | ------- |
-| `source_file_dependencies` | List of path **prefixes**. If any changed file equals a prefix or starts with `prefix/`, keep the step (or group); otherwise omit it. |
+| `source_file_dependencies` | Named preset (or list of presets) from [`ci_source_file_dependencies.yml`](https://github.com/vllm-project/vllm-omni/blob/main/.buildkite/common/ci_source_file_dependencies.yml). The uploader expands only that key; it does **not** scan `commands`. If any changed file equals a listed prefix or starts with `prefix/`, keep the step (or group); otherwise omit it. Inline path-prefix lists are still accepted. |
 | `mirror_hardwares` | Expand to `agents` + `plugins` (+ optional `image`) from `ci_mirror_hardwares.yml`. |
 
 ### Policy
 
-- **Always uploaded** (no key): groups outside **E2E Test**—Simple Test, Diffusion unit tests, Engine/Model Executor, Distributed, Custom Pipeline, Entrypoints (L2), LoRA / Entrypoints (L3).
-- **Diff-gated**: every **E2E Test** leaf job. List the smallest prefix set per step—pytest file(s), model code under `vllm_omni/model_executor/models/` or `vllm_omni/diffusion/models/`, plus `stage_input_processors/` and `vllm_omni/deploy/*.yaml` when applicable. A **group** may define the key instead; the whole group drops if no prefix matches.
+- **Always uploaded** (no key): L2/L3 groups outside **E2E Test**—Simple Test, Diffusion unit tests, Engine/Model Executor, Distributed, Custom Pipeline, Entrypoints (L2), LoRA / Entrypoints (L3).
+- **Diff-gated**: every **E2E Test** leaf job in L2/L3, L4 nightly leaf jobs (CUDA and NPU), and L5 weekly jobs whose `if` includes the `weekly-test` label (Reliability / Perf). Jobs gated only by `WEEKLY=1` or `NON_CRITICAL=1` have no `source_file_dependencies`. Registry layout: YAML anchors are model business code only (`vllm_omni/model_executor/models/`, `vllm_omni/diffusion/models/`, plus `stage_input_processors/` and `vllm_omni/deploy/*.yaml` when applicable). Job keys alias the anchor and **also** list the scripts that job runs (pytest files, `run_cov_split.sh --offline` / `--online` targets, example README runners). Feature keys stay cross-cutting. A **group** may define the key instead; the whole group drops if no prefix matches.
 
 ### YAML examples
 
 ```yaml
       - label: "Diffusion · Qwen Image Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen_image.py
-          - vllm_omni/diffusion/models/qwen_image/
+        source_file_dependencies: diffusion_qwen_image_function
+        # diffusion_qwen_image_function: *qwen_image + tests/e2e/online_serving/test_qwen_image.py
         commands:
           - pytest -s -v tests/e2e/online_serving/test_qwen_image.py -m 'core_model' ...
         mirror_hardwares: h100_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
+        source_file_dependencies: tts_qwen3_tts_function
+        # tts_qwen3_tts_function: *qwen3_tts + tests/e2e/online_serving/test_qwen3_tts_customvoice.py
         commands:
           - pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py ...
-        mirror_hardwares: l4_4
+        mirror_hardwares: l4_1
 ```
 
 ### Local dry-run
@@ -443,15 +446,16 @@ plugin, which provides the agent. `l4_*` jobs run on the EKS `l4-k8s` queue
 still needs `mount-buildkite-agent: true`.
 
 List both `run_cov_split.sh` and `pyproject.toml` in every opted-in job's
-`source_file_dependencies` — both change what the job measures, so without them a
+`source_file_dependencies` preset — both change what the job measures, so without them a
 change there is filtered out of normal PR builds and only surfaces in a later
 nightly. `tests/buildkite/test_upload_pipeline.py` covers the filter behavior with
 a synthetic job (it does not pin real merge labels).
-Editing only the surrounding CI YAML still does not schedule them, so a PR that
-touches just the wiring needs a full E2E run (or the commands run on a GPU host)
-to produce artifacts. When checking a new model's
-artifacts, compare `lines-covered` between the online and offline XML rather than
-just confirming both files exist.
+If no job-key prefix matches, editing the pipeline YAML being uploaded, or any
+path under the `source_filter_fallback` registry key, keeps every job in that
+upload (including coverage jobs) so the wiring can be validated before merge.
+When a job-key prefix already matches, bypass does not expand the selection. A
+change to a different pipeline YAML still does not schedule them. When checking a new model's artifacts, compare `lines-covered`
+between the online and offline XML rather than just confirming both files exist.
 
 ### Validation checklist
 

tests/buildkite/test_upload_pipeline.py

@@ -13,11 +13,15 @@ sys.path.insert(0, str(Path(__file__).resolve().parents[2] / ".buildkite" / "com
 from skip_ci import resolve_ci_decision  # noqa: E402
 from upload_pipeline import (  # noqa: E402
     CUDA_HF_TOKEN_EXPORT,
+    NIGHTLY_LABEL_IF,
+    _changed_files_for_source_filter,
     _expand_mirror_hardwares,
     _get_mirror_hw_selector,
     _load_bootstrap_steps,
+    _load_source_file_dependencies,
     _render_bootstrap_pipeline,
     _render_test_pipeline,
+    _resolve_source_file_dependencies,
 )
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -101,6 +105,26 @@ def test_npu_docs_only_does_not_upload_ready_on_nightly() -> None:
     assert 'build.env("NIGHTLY") == "1"' in by_key["upload-nightly-pipeline"]["if"]
 
 
+def test_nightly_label_if_is_only_nightly_test() -> None:
+    assert 'labels includes "nightly-test"' in NIGHTLY_LABEL_IF
+    forbidden = (
+        'includes "omni-test"',
+        'includes "tts-test"',
+        'includes "diffusion-x2iat-test"',
+        'includes "diffusion-x2v-test"',
+    )
+    for needle in forbidden:
+        assert needle not in NIGHTLY_LABEL_IF
+    for path in (
+        Path(".buildkite/cuda/test-nightly.yml"),
+        Path(".buildkite/npu/test-npu-nightly.yml"),
+        Path(".buildkite/common/scripts/upload_pipeline.py"),
+    ):
+        text = path.read_text(encoding="utf-8")
+        for needle in forbidden:
+            assert needle not in text, f"{path} still references {needle}"
+
+
 def test_yaml_gated_l45_only_does_not_unconditionally_build_image() -> None:
     rendered = _render([".buildkite/cuda/test-nightly.yml"])
     assert "if: true" not in rendered
@@ -366,8 +390,17 @@ def test_mirror_hw_typo_fails_closed(monkeypatch: pytest.MonkeyPatch) -> None:
         )
 
 
-def _surviving_labels(doc: dict, changed_files: list[str]) -> set[str]:
-    rendered = _render_test_pipeline(doc, changed_files=changed_files)
+def _surviving_labels(
+    doc: dict,
+    changed_files: list[str],
+    *,
+    pipeline_path: Path | None = None,
+) -> set[str]:
+    rendered = _render_test_pipeline(
+        doc,
+        changed_files=changed_files,
+        pipeline_path=pipeline_path,
+    )
     labels: set[str] = set()
 
     def walk(steps: list | None) -> None:
@@ -382,6 +415,17 @@ def _surviving_labels(doc: dict, changed_files: list[str]) -> set[str]:
     return labels
 
 
+def _iter_steps(doc: dict):
+    def walk(steps: list | None):
+        for step in steps or []:
+            if not isinstance(step, dict):
+                continue
+            yield step
+            yield from walk(step.get("steps"))
+
+    yield from walk(doc.get("steps"))
+
+
 # Synthetic coverage-style job: shared inputs that change what the split measures.
 _COVERAGE_SHARED_INPUTS_DOC = {
     "steps": [
@@ -426,3 +470,289 @@ def test_coverage_shared_inputs_ignored_for_unrelated_change() -> None:
     )
     assert "Coverage Pilot" not in labels
     assert "Unrelated Model Test" not in labels
+
+
+def _pipeline_dep_keys(path: Path) -> set[str]:
+    doc = yaml.safe_load(path.read_text(encoding="utf-8"))
+    keys: set[str] = set()
+
+    def walk(steps: list | None) -> None:
+        for step in steps or []:
+            if not isinstance(step, dict):
+                continue
+            deps = step.get("source_file_dependencies")
+            if isinstance(deps, str) and "/" not in deps:
+                keys.add(deps)
+            elif isinstance(deps, list) and deps and all("/" not in item for item in deps):
+                keys.update(deps)
+            walk(step.get("steps"))
+
+    walk((doc or {}).get("steps"))
+    return keys
+
+
+def test_pipeline_source_file_dependency_keys_are_registered() -> None:
+    _load_source_file_dependencies.cache_clear()
+    registry = _load_source_file_dependencies()
+    used = (
+        _pipeline_dep_keys(Path(".buildkite/cuda/test-ready.yml"))
+        | _pipeline_dep_keys(Path(".buildkite/cuda/test-merge.yml"))
+        | _pipeline_dep_keys(Path(".buildkite/cuda/test-nightly.yml"))
+        | _pipeline_dep_keys(Path(".buildkite/cuda/test-weekly.yml"))
+        | _pipeline_dep_keys(Path(".buildkite/npu/test-npu-nightly.yml"))
+    )
+    missing = used - set(registry)
+    assert not missing, f"unregistered source_file_dependencies keys: {sorted(missing)}"
+
+
+def test_source_file_dependencies_key_expands_from_registry() -> None:
+    doc = {
+        "steps": [
+            {
+                "label": "Diffusion · Qwen Image Test",
+                "source_file_dependencies": "diffusion_qwen_image_function",
+                "commands": ["pytest"],
+            },
+        ],
+    }
+    assert "Diffusion · Qwen Image Test" in _surviving_labels(
+        doc,
+        ["vllm_omni/diffusion/models/qwen_image/transformer.py"],
+    )
+    assert "Diffusion · Qwen Image Test" not in _surviving_labels(doc, ["vllm_omni/unrelated.py"])
+
+
+def test_registry_lists_pytest_targets() -> None:
+    _load_source_file_dependencies.cache_clear()
+    resolved = _resolve_source_file_dependencies(
+        {
+            "label": "Diffusion · Wan22 Test",
+            "source_file_dependencies": "diffusion_wan22_function",
+            "commands": [
+                "pytest -s -v tests/e2e/offline_inference/test_wan22_t2v.py "
+                "tests/e2e/online_serving/test_wan22_t2v.py -m 'advanced_model'",
+            ],
+        },
+    )
+    assert resolved is not None
+    assert "tests/e2e/offline_inference/test_wan22_t2v.py" in resolved
+    assert "tests/e2e/online_serving/test_wan22_t2v.py" in resolved
+    assert "vllm_omni/diffusion/models/wan2_2/" in resolved
+
+
+def test_coverage_key_lists_offline_online_scripts() -> None:
+    resolved = _resolve_source_file_dependencies(
+        {
+            "label": "TTS · Qwen3-TTS Base Test",
+            "source_file_dependencies": "tts_qwen3_tts_cov",
+            "commands": [
+                ".buildkite/common/scripts/run_cov_split.sh \\\n"
+                "  --offline tests/e2e/offline_inference/test_qwen3_tts_base.py \\\n"
+                "  --online tests/e2e/online_serving/test_qwen3_tts_base.py",
+            ],
+        },
+    )
+    assert resolved is not None
+    assert "tests/e2e/offline_inference/test_qwen3_tts_base.py" in resolved
+    assert "tests/e2e/online_serving/test_qwen3_tts_base.py" in resolved
+    assert ".buildkite/common/scripts/run_cov_split.sh" in resolved
+    assert "pyproject.toml" in resolved
+
+
+def test_source_file_dependencies_list_of_keys_concatenates() -> None:
+    resolved = _resolve_source_file_dependencies(
+        {
+            "label": "composed",
+            "source_file_dependencies": ["omni_qwen3_omni_function", "tts_qwen3_tts_function"],
+        },
+    )
+    assert resolved is not None
+    assert "vllm_omni/model_executor/models/qwen3_omni/" in resolved
+    assert "vllm_omni/model_executor/models/qwen3_tts/" in resolved
+    assert resolved.count("vllm_omni/model_executor/models/common/snake_activation.py") == 1
+
+
+def test_unknown_source_file_dependencies_key() -> None:
+    with pytest.raises(ValueError, match="unknown source_file_dependencies"):
+        _render_test_pipeline(
+            {"steps": [{"label": "bad", "source_file_dependencies": "not_a_real_key"}]},
+            changed_files=None,
+        )
+
+
+def test_source_file_dependencies_rejects_mixed_keys_and_paths() -> None:
+    with pytest.raises(ValueError, match="mixes registry keys and path prefixes"):
+        _resolve_source_file_dependencies(
+            {
+                "label": "bad",
+                "source_file_dependencies": ["omni_qwen3_omni_function", "tests/e2e/online_serving/test_qwen3_omni.py"],
+            },
+        )
+
+
+# Synthetic pipeline: selection depends only on listed deps, not on live job names.
+_SOURCE_FILTER_DOC = {
+    "steps": [
+        {
+            "group": "E2E Tests",
+            "if": 'build.env("NON_CRITICAL") == "1"',
+            "steps": [
+                {
+                    "label": "Dedicated E2E",
+                    "commands": ["pytest -sv tests/e2e/online_serving/test_magi2.py"],
+                },
+            ],
+        },
+        {
+            "label": "Omni Sweep",
+            "source_file_dependencies": ["tests/e2e/online_serving/test_qwen3_omni.py"],
+            "commands": ["pytest -sv tests/e2e/ -m omni"],
+        },
+        {
+            "label": "Z-Image Function",
+            "source_file_dependencies": [
+                "tests/e2e/online_serving/test_zimage_expansion.py",
+                "vllm_omni/diffusion/models/z_image/",
+            ],
+            "mirror_hardwares": "l4_4",
+            "commands": ["pytest -sv tests/e2e/online_serving/test_zimage_expansion.py"],
+        },
+        {
+            "label": "Tiny Model",
+            "source_file_dependencies": ["tests/e2e/online_serving/test_tiny.py"],
+            "commands": ["pytest -sv tests/e2e/ -m tiny"],
+        },
+        {
+            "label": "Wan Function",
+            "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": ["pytest -sv tests/e2e/offline_inference/test_wan22_t2v.py"],
+        },
+        {
+            "label": "Wan Perf",
+            "source_file_dependencies": ["vllm_omni/diffusion/models/wan2_2/"],
+            "commands": ["pytest -sv tests/dfx/perf/scripts/run_benchmark.py"],
+        },
+        {
+            "label": "Doc Test",
+            "source_file_dependencies": [
+                "tests/examples/offline_inference/test_text_to_image.py",
+                "tests/examples/online_serving/test_text_to_image.py",
+                "vllm_omni/diffusion/models/qwen_image/",
+                "vllm_omni/diffusion/models/z_image/",
+            ],
+            "commands": ["pytest -sv tests/examples/*/test_text_to_image.py"],
+        },
+    ],
+}
+
+
+def test_source_filter_ignores_unrelated_e2e_file() -> None:
+    """A sweep command is not a dependency; only listed paths select a keyed job."""
+    labels = _surviving_labels(_SOURCE_FILTER_DOC, ["tests/e2e/online_serving/test_magi2.py"])
+    assert labels == {"Dedicated E2E"}
+
+
+def test_source_filter_selects_job_by_listed_script_not_sibling() -> None:
+    labels = _surviving_labels(_SOURCE_FILTER_DOC, ["tests/e2e/online_serving/test_zimage_expansion.py"])
+    assert labels == {"Dedicated E2E", "Z-Image Function"}
+
+
+def test_source_filter_selects_every_job_sharing_a_path() -> None:
+    labels = _surviving_labels(_SOURCE_FILTER_DOC, ["vllm_omni/diffusion/models/wan2_2/transformer.py"])
+    assert labels == {"Dedicated E2E", "Wan Function", "Wan Perf"}
+
+
+def test_source_filter_selects_composed_doc_job_by_example_or_model() -> None:
+    for changed in (
+        "tests/examples/online_serving/test_text_to_image.py",
+        "vllm_omni/diffusion/models/z_image/transformer.py",
+        "vllm_omni/diffusion/models/qwen_image/foo.py",
+    ):
+        labels = _surviving_labels(_SOURCE_FILTER_DOC, [changed])
+        assert "Doc Test" in labels, changed
+        assert "Tiny Model" not in labels
+        assert "Omni Sweep" not in labels
+    assert "Doc Test" not in _surviving_labels(_SOURCE_FILTER_DOC, ["tests/e2e/online_serving/test_magi2.py"])
+
+
+def test_source_filter_strips_deps_and_expands_hardware(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setattr("upload_pipeline._get_mirror_hw_selector", lambda: "")
+    rendered = _render_test_pipeline(
+        _SOURCE_FILTER_DOC,
+        changed_files=["tests/e2e/online_serving/test_zimage_expansion.py"],
+    )
+    dumped = yaml.safe_dump(rendered)
+    assert "source_file_dependencies" not in dumped
+    assert "mirror_hardwares" not in dumped
+    z_image = next(step for step in _iter_steps(rendered) if step.get("label") == "Z-Image Function")
+    assert z_image["agents"]["queue"] == "l4-k8s"
+
+
+def test_source_filter_disabled_on_main_branch(monkeypatch: pytest.MonkeyPatch) -> None:
+    class _Ctx:
+        changed_files = ["vllm_omni/unrelated.py"]
+
+    monkeypatch.setenv("BUILDKITE_BRANCH", "main")
+    assert _changed_files_for_source_filter(_Ctx(), force_all=False, e2e_only=False) is None
+
+    monkeypatch.setenv("BUILDKITE_BRANCH", "feat/source-filter")
+    assert _changed_files_for_source_filter(_Ctx(), force_all=False, e2e_only=False) == [
+        "vllm_omni/unrelated.py",
+    ]
+    monkeypatch.setenv("BUILDKITE_BRANCH", "main")
+    assert _changed_files_for_source_filter(_Ctx(), force_all=True, e2e_only=False) is None
+
+
+def test_source_filter_fallback_is_fallback_when_no_job_key_matches(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    """Fallback only when no listed prefix matched; a matching prefix still wins."""
+    monkeypatch.setattr("upload_pipeline._get_mirror_hw_selector", lambda: "")
+    monkeypatch.setenv("BUILDKITE_BRANCH", "feat/nightly-yaml")
+    pipeline_yaml = Path(".buildkite/npu/test-npu-nightly.yml")
+    shared_paths = _load_source_file_dependencies()["source_filter_fallback"]
+    assert ".buildkite/common/scripts/upload_pipeline.py" in shared_paths
+
+    # Synthetic steps only — do not pin live Buildkite job labels.
+    doc = {
+        "steps": [
+            {"key": "ungated", "commands": ["true"]},
+            {
+                "key": "gated_a",
+                "source_file_dependencies": ["pkg/model_a/"],
+                "commands": ["true"],
+            },
+            {
+                "key": "gated_b",
+                "source_file_dependencies": ["pkg/model_b/"],
+                "commands": ["true"],
+            },
+        ],
+    }
+
+    def surviving_keys(changed_files: list[str]) -> set[str]:
+        rendered = _render_test_pipeline(
+            doc,
+            changed_files=changed_files,
+            pipeline_path=pipeline_yaml,
+        )
+        return {step["key"] for step in _iter_steps(rendered) if isinstance(step.get("key"), str)}
+
+    # Only pipeline YAML / shared uploader → no listed prefix match → keep every step.
+    for changed in [pipeline_yaml.as_posix(), *shared_paths]:
+        assert surviving_keys([changed]) == {"ungated", "gated_a", "gated_b"}, changed
+
+    # A different pipeline YAML is not a fallback for this upload.
+    assert surviving_keys([".buildkite/cuda/test-nightly.yml"]) == {"ungated"}
+
+    # A matching source prefix wins over fallback files in the same diff.
+    assert surviving_keys(
+        [
+            "pkg/model_a/transformer.py",
+            ".buildkite/common/scripts/upload_pipeline.py",
+        ],
+    ) == {"ungated", "gated_a"}

tests/e2e/accuracy/test_hidream_o1_image.py

@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
 
 from __future__ import annotations
 
@@ -16,7 +16,7 @@ from vllm_omni.diffusion.data import DiffusionParallelConfig
 from vllm_omni.diffusion.utils.image_output import extract_images_from_outputs
 from vllm_omni.inputs.data import OmniDiffusionSamplingParams
 
-pytestmark = [pytest.mark.full_model, pytest.mark.diffusion]
+pytestmark = [pytest.mark.slow, pytest.mark.diffusion]
 
 MODEL_ID = "HiDream-ai/HiDream-O1-Image"
 PROMPT = "A cat is sitting next to a sign that says 'HiDream-O1 vLLM-Omni'"

tests/e2e/offline_inference/test_lingbot_world_v2.py

@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
 """End-to-end smoke test for LingBot-World v2 generation."""
 
 from __future__ import annotations
@@ -37,7 +37,7 @@ _OMNI_RUNNER_PARAM = (
 )
 
 pytestmark = [
-    pytest.mark.slow,
+    pytest.mark.full_model,
     pytest.mark.diffusion,
     pytest.mark.skipif(
         not _HAS_INPUT_ASSETS,

tests/e2e/online_serving/minimax_h3/test_minimax_h3_dlo_dp2_fl2va.py

@@ -12,7 +12,7 @@ from tests.helpers.runtime import OmniServer, OpenAIClientHandler
 
 from ._common import assert_h3_video, dlo_params, run_dlo_wave, run_fl2va
 
-pytestmark = [pytest.mark.core_model, pytest.mark.advanced_model, pytest.mark.diffusion, pytest.mark.slow]
+pytestmark = [pytest.mark.advanced_model, pytest.mark.diffusion]
 H100_TWO_CARD_MARKS = hardware_marks(res={"cuda": "H100"}, num_cards=2)
 
 

tests/e2e/online_serving/minimax_h3/test_minimax_h3_dlo_dp2_ref2va.py

@@ -12,7 +12,7 @@ from tests.helpers.runtime import OmniServer, OpenAIClientHandler
 
 from ._common import assert_h3_video, dlo_params, run_dlo_wave, run_ref2va
 
-pytestmark = [pytest.mark.core_model, pytest.mark.advanced_model, pytest.mark.diffusion, pytest.mark.slow]
+pytestmark = [pytest.mark.advanced_model, pytest.mark.diffusion]
 H100_TWO_CARD_MARKS = hardware_marks(res={"cuda": "H100"}, num_cards=2)
 
 

tests/e2e/online_serving/minimax_h3/test_minimax_h3_fasth3_lora.py

@@ -21,7 +21,7 @@ from ._common import (
     post_sync,
 )
 
-pytestmark = [pytest.mark.core_model, pytest.mark.advanced_model, pytest.mark.diffusion, pytest.mark.slow]
+pytestmark = [pytest.mark.advanced_model, pytest.mark.diffusion]
 H100_TWO_CARD_MARKS = hardware_marks(res={"cuda": "H100"}, num_cards=2)
 
 

tests/e2e/online_serving/minimax_h3/test_minimax_h3_turbo_lora.py

@@ -20,7 +20,7 @@ from ._common import (
     turbo_params,
 )
 
-pytestmark = [pytest.mark.core_model, pytest.mark.advanced_model, pytest.mark.diffusion, pytest.mark.slow]
+pytestmark = [pytest.mark.advanced_model, pytest.mark.diffusion]
 H100_TWO_CARD_MARKS = hardware_marks(res={"cuda": "H100"}, num_cards=2)
 
 

tests/e2e/online_serving/test_lingbot_video.py

@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
 
 """Online serving smoke coverage for the dense LingBot-Video checkpoint."""
 
@@ -41,7 +41,7 @@ def _get_diffusion_feature_cases(model: str):
     ]
 
 
-@pytest.mark.slow
+@pytest.mark.full_model
 @pytest.mark.diffusion
 @pytest.mark.parametrize("omni_server", _get_diffusion_feature_cases(MODEL), indirect=True)
 def test_text_to_image_001(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:
@@ -63,7 +63,7 @@ def test_text_to_image_001(omni_server: OmniServer, openai_client: OpenAIClientH
     )
 
 
-@pytest.mark.slow
+@pytest.mark.full_model
 @pytest.mark.diffusion
 @pytest.mark.parametrize("omni_server", _get_diffusion_feature_cases(MODEL), indirect=True)
 def test_video_generation_modes_001(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:

tests/e2e/online_serving/test_lingbot_video_moe.py

@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
 
 """Single-GPU serving smoke for ``robbyant/lingbot-video-moe-30b-a3b``."""
 
@@ -41,7 +41,7 @@ def _get_server_cases(model: str):
     ]
 
 
-@pytest.mark.slow
+@pytest.mark.full_model
 @pytest.mark.diffusion
 @pytest.mark.parametrize("omni_server", _get_server_cases(MODEL), indirect=True)
 def test_text_to_image_moe(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:
@@ -63,7 +63,7 @@ def test_text_to_image_moe(omni_server: OmniServer, openai_client: OpenAIClientH
     )
 
 
-@pytest.mark.slow
+@pytest.mark.full_model
 @pytest.mark.diffusion
 @pytest.mark.parametrize("omni_server", _get_server_cases(MODEL), indirect=True)
 def test_video_generation_modes_moe(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None:

tests/e2e/online_serving/test_magi2.py

@@ -8,7 +8,7 @@ It exercises the recommended resident SP4 topology through ``/v1/videos``.
 
 From ``tests/``::
 
-    pytest -s -v e2e/online_serving/test_magi2.py -m "advanced_model and diffusion" --run-level=advanced_model
+    pytest -s -v e2e/online_serving/test_magi2.py -m "slow and diffusion" --run-level=full_model
 """
 
 import json
@@ -27,8 +27,7 @@ PROMPT = "A red fox walks through fresh snow while wind moves the pine branches.
 FOUR_CARD_MARKS = hardware_marks(res={"cuda": "H100"}, num_cards=4)
 
 
-@pytest.mark.core_model
-@pytest.mark.advanced_model
+@pytest.mark.slow
 @pytest.mark.diffusion
 @pytest.mark.parametrize(
     "omni_server",

tests/e2e/online_serving/test_minimax_h3_dlo_dp2_t2va.py

@@ -111,7 +111,6 @@ def _run_t2va_request(client: OpenAIClientHandler, seed: int) -> bytes:
 @pytest.mark.core_model
 @pytest.mark.advanced_model
 @pytest.mark.diffusion
-@pytest.mark.slow
 @pytest.mark.parametrize(
     "omni_server",
     [

tools/pre_commit/check_buildkite.py

@@ -27,6 +27,7 @@ from upload_pipeline import _render_test_pipeline  # noqa: E402
 
 SKIP_FILES = {
     ".buildkite/common/ci_mirror_hardwares.yml",
+    ".buildkite/common/ci_source_file_dependencies.yml",
     ".buildkite/npu/pipeline-npu-a3.yml",
 }