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