Files
vllm-omni/.buildkite/test-amd.yaml
T
20a8fe1dcc [Test] L2 & L3 Test Case Stratification Design for Omni Model (#1272)
Signed-off-by: wangyu31577 <wangyu31577@hundsun.com>
Signed-off-by: yenuo26 <410167048@qq.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: wangyu31577 <wangyu31577@hundsun.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-02-12 09:56:35 +08:00

117 lines
3.5 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
- pytest -s -v tests/e2e/offline_inference/test_t2i_model.py
- label: "Diffusion Images API LoRA E2E"
timeout_in_minutes: 20
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
- pytest -s -v tests/e2e/online_serving/test_images_generations_lora.py
- label: "Diffusion Model CPU offloading Test"
timeout_in_minutes: 20
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
- pytest -s -v tests/e2e/offline_inference/test_diffusion_cpu_offload.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
- pytest -s -v -m 'core_model and cache and diffusion and not distributed_rocm and MI325'
- label: "Diffusion Sequence Parallelism Test"
timeout_in_minutes: 20
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
- pytest -s -v tests/e2e/offline_inference/test_sequence_parallel.py -m core_model
- label: "Diffusion Tensor Parallelism Test"
timeout_in_minutes: 20
agent_pool: mi325_2
depends_on: amd-build
commands:
- export GPU_ARCHS=gfx942
- export VLLM_LOGGING_LEVEL=DEBUG
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- pytest -s -v tests/e2e/offline_inference/test_zimage_parallelism.py
- label: "Diffusion GPU Worker Test"
timeout_in_minutes: 20
agent_pool: mi325_2
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- pytest -s -v tests/diffusion/test_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
- 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 VLLM_TEST_CLEAN_GPU_MEMORY="1"
- pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
- pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py
- pytest -s -v tests/engine/test_async_omni_engine_abort.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
- pytest -s -v tests/e2e/online_serving/test_image_gen_edit.py