Files
vllm-omni/.buildkite/test-amd.yaml
T
2025-12-21 11:51:37 +08:00

54 lines
1.8 KiB
YAML

steps:
- label: "Diffusion Model Test"
timeout_in_minutes: 15
agent_pool: mi325_2
depends_on: amd-build
mirror_hardwares: [amdexperimental, amdproduction, amdtentative]
grade: Blocking
commands:
- export GPU_ARCHS=gfx942
- export MIOPEN_DEBUG_CONV_DIRECT=0
- export MIOPEN_DEBUG_CONV_GEMM=0
- export VLLM_ROCM_USE_AITER=1
- export VLLM_ROCM_USE_AITER_MHA=1
- export VLLM_ROCM_USE_AITER_LINEAR=0
- export VLLM_ROCM_USE_AITER_RMSNORM=0
- pytest -s -v tests/e2e/offline_inference/test_t2i_model.py
- label: "Diffusion Cache Backend Test"
timeout_in_minutes: 15
agent_pool: mi325_1
depends_on: amd-build
mirror_hardwares: [amdexperimental, amdproduction, amdtentative]
grade: Blocking
commands:
- export GPU_ARCHS=gfx942
- export VLLM_LOGGING_LEVEL=DEBUG
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- export MIOPEN_DEBUG_CONV_DIRECT=0
- export MIOPEN_DEBUG_CONV_GEMM=0
- export VLLM_ROCM_USE_AITER=1
- export VLLM_ROCM_USE_AITER_MHA=1
- export VLLM_ROCM_USE_AITER_LINEAR=0
- export VLLM_ROCM_USE_AITER_RMSNORM=0
- pytest -s -v tests/e2e/offline_inference/test_cache_dit.py tests/e2e/offline_inference/test_teacache.py
- label: "Omni Model Test Qwen2-5-Omni"
timeout_in_minutes: 15
agent_pool: mi325_2
depends_on: amd-build
mirror_hardwares: [amdexperimental, amdproduction, amdtentative]
grade: Blocking
commands:
- export GPU_ARCHS=gfx942
- export VLLM_LOGGING_LEVEL=DEBUG
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- export MIOPEN_DEBUG_CONV_DIRECT=0
- export MIOPEN_DEBUG_CONV_GEMM=0
- export VLLM_ROCM_USE_AITER=1
- export VLLM_ROCM_USE_AITER_MHA=1
- export VLLM_ROCM_USE_AITER_LINEAR=0
- export VLLM_ROCM_USE_AITER_RMSNORM=0
- pytest -s -v tests/e2e/offline_inference/test_qwen2_5_omni.py