vllm-omni/.buildkite/common/ci_source_file_dependencies.yml

# 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/engine/async_omni_engine.py
  - vllm_omni/entrypoints/omni_base.py
  - 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
  - vllm_omni/worker_v2/
  - vllm_omni/core/sched/
  - vllm_omni/distributed/omni_connectors/
  - vllm_omni/config/stage_config.py
  - vllm_omni/config/omni_config.py
  - vllm_omni/engine/orchestrator.py
  - vllm_omni/engine/stage_engine_core_proc.py
  - vllm_omni/deploy/qwen3_tts_mrv2.yaml
  - vllm_omni/deploy/qwen3_tts_high_concurrency_mrv2.yaml
  - vllm_omni/deploy/qwen3_tts_high_concurrency_mrv2_b4.yaml

x-minicpmo-4-5: &minicpmo_4_5
  - vllm_omni/engine/async_omni_engine.py
  - vllm_omni/entrypoints/omni_base.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
  - 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/engine/duplex_omni_engine.py
  - vllm_omni/engine/duplex_orchestrator.py
  - vllm_omni/engine/omni_engine_base.py
  - vllm_omni/entrypoints/duplex/
  - vllm_omni/entrypoints/duplex_omni.py
  - vllm_omni/entrypoints/async_omni_base.py
  - vllm_omni/protocol/
  - vllm_omni/clients/
  - 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/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/engine/async_omni_engine.py
  - vllm_omni/entrypoints/omni_base.py
  - 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/engine/async_omni_engine.py
  - vllm_omni/entrypoints/omni_base.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

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/
  - vllm_omni/diffusion/layers/indexed_modulation.py

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:
  # Hardware presets and shared test helpers. 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/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 ---
  entrypoints_function:
    - tests/entrypoints/
    - vllm_omni/entrypoints/

  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_duplex_eval_ci:
    - *minicpmo_4_5
    - *minicpmo_4_5_duplex
    - tests/e2e/accuracy/omni_duplex_eval/**
    - tests/e2e/online_serving/helpers/minicpmo_4_5_duplex.py
    - vllm_omni/benchmarks/duplex/**
    - vllm_omni/entrypoints/cli/benchmark/omni_duplex_eval.py

  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_minicpmo_4_5_window.py
    - tests/e2e/online_serving/helpers/minicpmo_window_e2e.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/engine/test_duplex_omni_engine.py
    - tests/engine/test_duplex_orchestrator.py
    - tests/entrypoints/duplex/
    - tests/entrypoints/test_duplex_omni.py
    - tests/entrypoints/openai_api/test_duplex_api_server.py
    - tests/model_executor/models/minicpmo_4_5/duplex/
    - tests/protocol/

  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/offline_inference/test_device_postprocess_equivalence.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_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_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
    - tests/e2e/offline_inference/test_qwen_image_autoround_w4a16_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
    - tests/e2e/accuracy/test_hunyuan_image3_lora.py
    - vllm_omni/diffusion/lora/

  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_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_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_sana_video_function:
    - *sana_video
    - tests/e2e/online_serving/test_sana_video_expansion.py
    - tests/e2e/accuracy/sana_video/

  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_expansion.py
    - tests/e2e/online_serving/test_lingbot_video_moe.py
    - tests/e2e/offline_inference/test_lingbot_world_v2.py

  diffusion_lingbot_perf:
    - *lingbot_video
    - tests/dfx/perf/scripts/run_benchmark.py
    - tests/dfx/perf/tests/test_lingbot_video_vllm_omni.json


  # 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/