vLLM/.buildkite/test_areas/entrypoints.yaml

group: Entrypoints
depends_on: 
  - image-build
steps:
- label: Entrypoints Unit Tests
  key: entrypoints-unit-tests
  timeout_in_minutes: 10
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - vllm/entrypoints
  - tests/entrypoints/unit_tests
  - tests/entrypoints/weight_transfer
  commands:
  - pytest -v -s entrypoints/unit_tests
  - pytest -v -s entrypoints/weight_transfer

- label: Entrypoints Integration (LLM)
  key: entrypoints-integration-llm
  timeout_in_minutes: 40
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - vllm/
  - tests/entrypoints/llm
  commands:
  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
  - pytest -v -s entrypoints/llm --ignore=entrypoints/llm/test_generate.py --ignore=entrypoints/llm/test_collective_rpc.py --ignore=entrypoints/llm/offline_mode
  - pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
  - pytest -v -s entrypoints/llm/offline_mode # Needs to avoid interference with other tests
  mirror:
    amd:
      device: mi325_1
      depends_on:
      - image-build-amd

- label: Entrypoints Integration (API Server)
  key: entrypoints-integration-api-server
  device: h200_35gb
  timeout_in_minutes: 130
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - vllm/
  - tests/entrypoints/serve
  - tests/entrypoints/scale_out
  commands:
  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
  - pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc
  - PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc
  - pytest -v -s entrypoints/scale_out
  mirror:
    amd:
      device: mi325_1
      depends_on:
      - image-build-amd

- label: Entrypoints Integration (API Server OpenAI - Part 1)
  key: entrypoints-integration-api-server-openai-part-1
  timeout_in_minutes: 50
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - vllm/
  - tests/entrypoints/openai
  - tests/entrypoints/test_chat_utils
  commands:
  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness
  mirror:
    amd:
      device: mi325_1
      timeout_in_minutes: 80
      depends_on:
      - image-build-amd

- label: Entrypoints Integration (API Server OpenAI - Part 2)
  key: entrypoints-integration-api-server-openai-part-2
  timeout_in_minutes: 50
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - vllm/
  - tests/entrypoints/openai
  - tests/entrypoints/test_chat_utils
  commands:
  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
  - pytest -v -s entrypoints/openai/chat_completion
  - pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
  mirror:
    amd:
      device: mi325_1
      timeout_in_minutes: 80
      depends_on:
      - image-build-amd

- label: Entrypoints Integration (API Server Generate)
  key: entrypoints-integration-api-server-generate
  timeout_in_minutes: 50
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - vllm/
  - tests/tool_use
  - tests/entrypoints/tool_parsers
  - tests/entrypoints/anthropic
  - tests/entrypoints/generate
  commands:
  - pytest -v -s tool_use
  - pytest -v -s entrypoints/tool_parsers
  - pytest -v -s entrypoints/generate
  - pytest -v -s entrypoints/anthropic
  mirror:
    amd:
      device: mi325_1
      timeout_in_minutes: 60
      depends_on:
      - image-build-amd

- label: Entrypoints Integration (Responses API)
  key: entrypoints-integration-responses-api
  timeout_in_minutes: 50
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - vllm/
  - tests/entrypoints/openai/responses
  commands:
  - pytest -v -s entrypoints/openai/responses

- label: Entrypoints Integration (Speech to Text)
  device: h200_35gb
  key: entrypoints-integration-speech_to_text
  timeout_in_minutes: 50
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - vllm/
  - tests/entrypoints/speech_to_text
  commands:
  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
  - pytest -v -s entrypoints/speech_to_text

- label: Entrypoints Integration (Multimodal)
  device: h200_35gb
  key: entrypoints-integration-multimodal
  timeout_in_minutes: 50
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - vllm/
  - tests/entrypoints/multimodal
  commands:
  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
  - pytest -v -s entrypoints/multimodal

- label: Entrypoints Integration (Pooling)
  key: entrypoints-integration-pooling
  timeout_in_minutes: 50
  working_dir: "/vllm-workspace/tests"
  source_file_dependencies:
  - vllm/
  - tests/entrypoints/pooling
  commands:
  - export VLLM_WORKER_MULTIPROC_METHOD=spawn
  - pytest -v -s entrypoints/pooling

- label: OpenAI API Correctness
  key: openai-api-correctness
  timeout_in_minutes: 30
  device: h200_18gb
  source_file_dependencies:
  - csrc/
  - vllm/entrypoints/openai/
  commands: # LMEval
  - pytest -s entrypoints/openai/correctness/
  mirror:
    amd:
      device: mi325_1
      depends_on:
      - image-build-amd
      source_file_dependencies:
      - csrc/
      - vllm/entrypoints/openai/
      - vllm/model_executor/layers/
      - vllm/v1/attention/backends/
      - vllm/v1/attention/selector.py
      - vllm/_aiter_ops.py
      - vllm/platforms/rocm.py
      - vllm/model_executor/model_loader/
      commands:
      - bash ../tools/install_torchcodec_rocm.sh || exit 1
      - pytest -s entrypoints/openai/correctness/