group: Engine
depends_on:
  - image-build
steps:
- label: Engine
  timeout_in_minutes: 15
  source_file_dependencies:
  - vllm/
  - tests/engine
  - tests/test_sequence
  - tests/test_config
  - tests/test_logger
  - tests/test_vllm_port
  commands:
  - pytest -v -s engine test_sequence.py test_config.py test_logger.py test_vllm_port.py

- label: Engine (1 GPU)
  timeout_in_minutes: 30
  source_file_dependencies:
    - vllm/v1/engine/
    - tests/v1/engine/
  commands:
    - pytest -v -s v1/engine/test_preprocess_error_handling.py
    - pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py

- label: e2e Scheduling (1 GPU)
  timeout_in_minutes: 30
  source_file_dependencies:
    - vllm/v1/
    - tests/v1/e2e/general/
  commands:
    - pytest -v -s v1/e2e/general/test_async_scheduling.py

- label: e2e Core (1 GPU)
  timeout_in_minutes: 30
  source_file_dependencies:
    - vllm/v1/
    - tests/v1/e2e/general/
  commands:
    - pytest -v -s v1/e2e/general --ignore v1/e2e/general/test_async_scheduling.py

- label: V1 e2e (2 GPUs)
  timeout_in_minutes: 60 # TODO: Fix timeout after we have more confidence in the test stability
  optional: true
  num_devices: 2
  source_file_dependencies:
    - vllm/
    - tests/v1/e2e
  commands:
    # Only run tests that need exactly 2 GPUs
    - pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "tensor_parallelism"
  mirror:
    amd:
      device: mi325_2
      depends_on:
      - image-build-amd

- label: V1 e2e (4 GPUs)
  timeout_in_minutes: 60 # TODO: Fix timeout after we have more confidence in the test stability
  optional: true
  num_devices: 4
  source_file_dependencies:
    - vllm/
    - tests/v1/e2e
  commands:
    # Only run tests that need 4 GPUs
    - pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "eagle_correctness_heavy"
  mirror:
    amd:
      device: mi325_4
      depends_on:
      - image-build-amd

- label: V1 e2e (4xH100)
  timeout_in_minutes: 60
  device: h100
  num_devices: 4
  optional: true
  source_file_dependencies:
    - vllm/v1/attention/backends/utils.py
    - vllm/v1/worker/gpu_model_runner.py
    - tests/v1/e2e/test_hybrid_chunked_prefill.py
  commands:
    - pytest -v -s v1/e2e/test_hybrid_chunked_prefill.py