Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
99 lines
3.2 KiB
YAML
99 lines
3.2 KiB
YAML
group: Entrypoints
|
|
depends_on:
|
|
- image-build
|
|
steps:
|
|
- label: Entrypoints Unit Tests
|
|
timeout_in_minutes: 10
|
|
working_dir: "/vllm-workspace/tests"
|
|
source_file_dependencies:
|
|
- vllm/entrypoints
|
|
- tests/entrypoints/
|
|
commands:
|
|
- pytest -v -s entrypoints/openai/tool_parsers
|
|
- pytest -v -s entrypoints/ --ignore=entrypoints/llm --ignore=entrypoints/rpc --ignore=entrypoints/sleep --ignore=entrypoints/instrumentator --ignore=entrypoints/openai --ignore=entrypoints/offline_mode --ignore=entrypoints/test_chat_utils.py --ignore=entrypoints/pooling
|
|
|
|
- label: Entrypoints Integration (LLM)
|
|
timeout_in_minutes: 40
|
|
working_dir: "/vllm-workspace/tests"
|
|
source_file_dependencies:
|
|
- vllm/
|
|
- tests/entrypoints/llm
|
|
- tests/entrypoints/offline_mode
|
|
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
|
|
- pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process
|
|
- pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
|
|
|
|
- label: Entrypoints Integration (API Server 1)
|
|
timeout_in_minutes: 130
|
|
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/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
|
|
- pytest -v -s entrypoints/test_chat_utils.py
|
|
mirror:
|
|
amd:
|
|
device: mi325_1
|
|
depends_on:
|
|
- image-build-amd
|
|
|
|
- label: Entrypoints Integration (API Server 2)
|
|
timeout_in_minutes: 130
|
|
working_dir: "/vllm-workspace/tests"
|
|
source_file_dependencies:
|
|
- vllm/
|
|
- tests/entrypoints/rpc
|
|
- tests/entrypoints/instrumentator
|
|
- tests/tool_use
|
|
commands:
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
- pytest -v -s entrypoints/instrumentator
|
|
- PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/rpc
|
|
- pytest -v -s tool_use
|
|
|
|
- label: 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: 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 V1
|
|
timeout_in_minutes: 50
|
|
source_file_dependencies:
|
|
- vllm/
|
|
- tests/v1
|
|
commands:
|
|
- pytest -v -s v1/entrypoints
|
|
mirror:
|
|
amd:
|
|
device: mi325_1
|
|
depends_on:
|
|
- image-build-amd
|
|
|
|
- label: OpenAI API Correctness
|
|
timeout_in_minutes: 30
|
|
source_file_dependencies:
|
|
- csrc/
|
|
- vllm/entrypoints/openai/
|
|
- vllm/model_executor/models/whisper.py
|
|
commands: # LMEval+Transcription WER check
|
|
- pytest -s entrypoints/openai/correctness/
|