biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI] split Entrypoints Integration (API Server 1) into 3 jobs (#37882)

Browse Source 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
Kunshang Ji
2026-03-24 01:37:56 +08:00
committed by GitHub
parent 1cbbcfe8a3
commit 91fd695b75
1 changed files with 31 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.buildkite/test_areas/entrypoints.yaml
View File

@@ -25,8 +25,8 @@ steps:
- pytest -v -s entrypoints/llm/test_generate.py # it needs a clean process - 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 - pytest -v -s entrypoints/offline_mode # Needs to avoid interference with other tests
- label: Entrypoints Integration (API Server 1) - label: Entrypoints Integration (API Server openai - Part 1)
timeout_in_minutes: 130 timeout_in_minutes: 50
working_dir: "/vllm-workspace/tests" working_dir: "/vllm-workspace/tests"
source_file_dependencies: source_file_dependencies:
- vllm/ - vllm/
@@ -34,7 +34,24 @@ steps:
- tests/entrypoints/test_chat_utils - tests/entrypoints/test_chat_utils
commands: commands:
- export VLLM_WORKER_MULTIPROC_METHOD=spawn - 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/chat_completion/test_oot_registration.py --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/test_multi_api_servers.py - pytest -v -s entrypoints/openai/chat_completion --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: 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:
- pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
- pytest -v -s entrypoints/openai/speech_to_text/
- pytest -v -s entrypoints/test_chat_utils.py - pytest -v -s entrypoints/test_chat_utils.py
mirror: mirror:
amd: amd:
@@ -42,6 +59,17 @@ steps:
depends_on: depends_on:
- image-build-amd - image-build-amd
- label: Entrypoints Integration (API Server openai - Part 3)
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/chat_completion --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/speech_to_text/ --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/test_multi_api_servers.py
- label: Entrypoints Integration (API Server 2) - label: Entrypoints Integration (API Server 2)
timeout_in_minutes: 130 timeout_in_minutes: 130
working_dir: "/vllm-workspace/tests" working_dir: "/vllm-workspace/tests"