steps:

- label: "Diffusion Model Test"
  timeout_in_minutes: 30
  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_z_image.py

- label: "Diffusion Images API LoRA E2E"
  timeout_in_minutes: 30
  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/diffusion/lora/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/diffusion/offloader/test_diffusion_cpu_offload.py
    - pytest -s -v tests/diffusion/offloader/test_diffusion_layerwise_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/diffusion/distributed/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/diffusion/distributed/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_expansion.py
    - pytest -s -v tests/engine/test_async_omni_engine_abort.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_ROCM_USE_AITER=0
    - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py
    - pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py


- label: "Omni Sleep Mode Test"
  timeout_in_minutes: 40
  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/entrypoints/test_omni_sleep_mode.py -m "advanced_model and omni and MI325" --run-level "advanced_model"