107 lines
3.4 KiB
YAML
107 lines
3.4 KiB
YAML
steps:
|
|
|
|
- label: "Diffusion Model Test"
|
|
timeout_in_minutes: 20
|
|
agent_pool: mi325_2
|
|
depends_on: amd-build
|
|
mirror_hardwares: [amdproduction]
|
|
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: [amdproduction]
|
|
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: "Diffusion Parallelism Test"
|
|
timeout_in_minutes: 15
|
|
agent_pool: mi325_2
|
|
depends_on: amd-build
|
|
mirror_hardwares: [amdproduction]
|
|
grade: Blocking
|
|
commands:
|
|
- export MIOPEN_DEBUG_CONV_DIRECT=0
|
|
- export MIOPEN_DEBUG_CONV_GEMM=0
|
|
- pytest -s -v tests/e2e/offline_inference/test_sequence_parallel.py
|
|
|
|
- label: "Diffusion GPU Worker Test"
|
|
timeout_in_minutes: 20
|
|
agent_pool: mi325_2
|
|
depends_on: amd-build
|
|
mirror_hardwares: [amdproduction]
|
|
grade: Blocking
|
|
commands:
|
|
- export MIOPEN_DEBUG_CONV_DIRECT=0
|
|
- export MIOPEN_DEBUG_CONV_GEMM=0
|
|
- pytest -s -v tests/diffusion/test_gpu_diffusion_worker.py
|
|
|
|
- label: "Omni Model Test Qwen2-5-Omni"
|
|
timeout_in_minutes: 15
|
|
agent_pool: mi325_2
|
|
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
|
|
- 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
|
|
|
|
- label: "Omni Model Test Qwen3-Omni"
|
|
timeout_in_minutes: 15
|
|
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 MIOPEN_DEBUG_CONV_DIRECT=0
|
|
- export MIOPEN_DEBUG_CONV_GEMM=0
|
|
- pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py
|
|
|
|
- label: "Diffusion Image Edit Test"
|
|
timeout_in_minutes: 15
|
|
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
|
|
- 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/online_serving/test_i2i_multi_image_input.py
|