anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity
Files
bab6f62d2f5697c0cbac7da6a6eb2bef2248df8f
vllm-omni/.buildkite/test-amd-ready.yaml
T
Zhang JianandClaude Opus 4.6 17acd0589a [Test] Add Stable Audio offline e2e TeaCache Test (#2377) 
Signed-off-by: Zhang <jianmusings@gmail.com>
Signed-off-by: Zhang Jian <jianmusings@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-14 15:05:12 +08:00

241 lines
8.2 KiB
YAML
Raw Blame History

steps:
- label: "Simple Unit Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- export VLLM_ROCM_USE_AITER=0
- "timeout 20m pytest -v -s -m 'core_model and cpu' --cov=vllm_omni --cov-branch --cov-report=term-missing --cov-report=html --cov-report=xml"
- label: "Voxtral TTS CUDA Unit Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- timeout 10m pytest -s -v tests/model_executor/models/voxtral_tts/test_cuda_graph_acoustic_transformer.py
- label: "Diffusion Model Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- timeout 30m pytest -s -v tests/e2e/offline_inference/test_t2i_model.py -m "core_model and diffusion" --run-level "core_model"
- label: "Diffusion Batching Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- timeout 20m pytest -s -v tests/e2e/offline_inference/test_qwen_image_diffusion_batching.py -m "core_model and diffusion" --run-level "core_model"
- label: "Custom Pipeline Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- timeout 20m pytest -s -v tests/e2e/offline_inference/custom_pipeline/ -m "core_model"
- label: "Diffusion Model CPU offloading Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- export VLLM_LOGGING_LEVEL=DEBUG
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- |
timeout 20m bash -c '
set +e
pytest -s -v tests/e2e/offline_inference/test_diffusion_cpu_offload.py
EXIT1=\$?
pytest -s -v tests/e2e/offline_inference/test_diffusion_layerwise_offload.py
EXIT2=\$?
exit \$((EXIT1 | EXIT2))
'
## ISSUE depends on `diffusers` package: https://github.com/huggingface/diffusers/issues/13274
# - label: "Audio Generation Model Test"
# agent_pool: mi325_1
# depends_on: amd-build
# mirror_hardwares: [amdproduction]
# grade: Blocking
# commands:
# - export GPU_ARCHS=gfx942
# - export VLLM_LOGGING_LEVEL=DEBUG
# - export VLLM_WORKER_MULTIPROC_METHOD=spawn
# - timeout 20m pytest -s -v tests/e2e/offline_inference/test_stable_audio_expansion.py -m "advanced_model and diffusion and L4" --run-level advanced_model
- label: "Diffusion Cache Backend Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- export GPU_ARCHS=gfx942
- export VLLM_LOGGING_LEVEL=DEBUG
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- timeout 15m pytest -s -v -m "core_model and cache and diffusion and not distributed_cuda and L4"
- label: "Diffusion Sequence Parallelism Test"
agent_pool: mi325_2
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- export VLLM_LOGGING_LEVEL=DEBUG
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- timeout 20m pytest -s -v tests/e2e/offline_inference/test_sequence_parallel.py -m core_model
- label: "Diffusion GPU Worker Test"
agent_pool: mi325_2
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- timeout 20m pytest -s -v tests/diffusion/test_diffusion_worker.py
- label: "Engine Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- |
timeout 15m bash -c '
pytest -s -v tests/engine/test_async_omni_engine_abort.py
'
# NOTE: This test is not running any thing. It is skipped and deselected.
# Currently it is = 1 skipped, 1 deselected, 17 warnings in 0.03s ======
# - label: "Omni Model Test Qwen2-5-Omni"
# agent_pool: mi325_2
# depends_on: amd-build
# mirror_hardwares: [amdproduction]
# grade: Blocking
# commands:
# - export VLLM_LOGGING_LEVEL=DEBUG
# - export VLLM_WORKER_MULTIPROC_METHOD=spawn
# - timeout 20m pytest -s -v tests/e2e/offline_inference/test_qwen2_5_omni.py -m "core_model" --run-level "core_model"
# - label: "Omni Model Test Qwen3-Omni"
# agent_pool: mi325_2
# depends_on: amd-build
# mirror_hardwares: [amdproduction]
# grade: Blocking
# commands:
# - export VLLM_LOGGING_LEVEL=DEBUG
# - export VLLM_WORKER_MULTIPROC_METHOD=spawn
# - export VLLM_TEST_CLEAN_GPU_MEMORY=1
# - timeout 10m pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
# - timeout 20m pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py -m "core_model" --run-level "core_model"
- label: "MiMo-Audio E2E Test with H100"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- |
timeout 30m bash -c '
export VLLM_LOGGING_LEVEL=DEBUG
export VLLM_WORKER_MULTIPROC_METHOD=spawn
pytest -s -v tests/e2e/online_serving/test_mimo_audio.py -m "core_model" --run-level "core_model"
'
- label: "Qwen3-TTS E2E Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- export VLLM_LOGGING_LEVEL=DEBUG
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
- timeout 30m pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m "core_model" --run-level "core_model"
- label: "Voxtral-TTS E2E Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- |
timeout 20m bash -c '
export VLLM_LOGGING_LEVEL=DEBUG
export VLLM_WORKER_MULTIPROC_METHOD=spawn
pytest -s -v tests/e2e/online_serving/test_voxtral_tts.py -m "advanced_model" --run-level "advanced_model"
pytest -s -v tests/e2e/offline_inference/test_voxtral_tts.py -m "advanced_model" --run-level "advanced_model"
'
- label: "Diffusion Image Edit Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- export GPU_ARCHS=gfx942
- export VLLM_LOGGING_LEVEL=DEBUG
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- timeout 20m pytest -s -v tests/e2e/online_serving/test_image_gen_edit.py
# TODO: Bagel test on ROCm is very unstable. @tjtanaa
# Need to debug before reneable numerical changes across large PRs
# - label: "Bagel Text2Img Model Test"
# agent_pool: mi325_1
# depends_on: amd-build
# mirror_hardwares: [amdproduction]
# grade: Blocking
# commands:
# - export GPU_ARCHS=gfx942
# - export VLLM_TEST_CLEAN_GPU_MEMORY=1
# - export VLLM_LOGGING_LEVEL=DEBUG
# - export VLLM_WORKER_MULTIPROC_METHOD=spawn
# - export VLLM_ROCM_USE_AITER_RMSNORM=0
# - timeout 30m pytest -s -v tests/e2e/offline_inference/test_bagel_text2img.py -m "core_model" --run-level "core_model" -k "rocm"
# - label: "Bagel Img2Img Model Test"
# agent_pool: mi325_1
# depends_on: amd-build
# mirror_hardwares: [amdproduction]
# grade: Blocking
# commands:
# - export GPU_ARCHS=gfx942
# - export VLLM_TEST_CLEAN_GPU_MEMORY=1
# - export VLLM_LOGGING_LEVEL=DEBUG
# - export VLLM_WORKER_MULTIPROC_METHOD=spawn
# - export VLLM_ROCM_USE_AITER_RMSNORM=0
# - timeout 30m pytest -s -v tests/e2e/offline_inference/test_bagel_img2img.py -m "core_model" --run-level "core_model" -k "rocm"
# - label: "Bagel Online Serving Test"
# agent_pool: mi325_1
# depends_on: amd-build
# mirror_hardwares: [amdproduction]
# grade: Blocking
# commands:
# - export GPU_ARCHS=gfx942
# - export VLLM_TEST_CLEAN_GPU_MEMORY=1
# - export VLLM_IMAGE_FETCH_TIMEOUT=60
# - export VLLM_LOGGING_LEVEL=DEBUG
# - export VLLM_WORKER_MULTIPROC_METHOD=spawn
# - export VLLM_ROCM_USE_AITER_RMSNORM=0
# - timeout 40m pytest -s -v tests/e2e/online_serving/test_bagel_online.py -m "core_model" --run-level "core_model" -k "rocm"
- label: "CosyVoice3-TTS E2E Test"
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- |
timeout 20m bash -c '
pytest -s -v tests/e2e/online_serving/test_cosyvoice3_tts.py -m "core_model" --run-level "core_model"
'
Reference in new issue View Git Blame Copy Permalink