xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 07:55:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(api): Return 503 on /health when engine is dead (#24897)

Browse Source 
Signed-off-by: dongbo910220 <1275604947@qq.com>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
dongbo910220 2025-09-18 22:29:40 +08:00 committed by GitHub
parent 072d7e53e5
commit 67244c86f0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/entrypoints/openai/api_server.py
View File

@ -103,6 +103,7 @@ from vllm.transformers_utils.tokenizer import MistralTokenizer
from vllm.usage.usage_lib import UsageContext
from vllm.utils import (Device, FlexibleArgumentParser, decorate_logs,
is_valid_ipv6_address, set_ulimit)
from vllm.v1.engine.exceptions import EngineDeadError
from vllm.v1.metrics.prometheus import get_prometheus_registry
from vllm.version import __version__ as VLLM_VERSION
@ -351,8 +352,11 @@ def engine_client(request: Request) -> EngineClient:
@router.get("/health", response_class=Response)
async def health(raw_request: Request) -> Response:
"""Health check."""
await engine_client(raw_request).check_health()
return Response(status_code=200)
try:
await engine_client(raw_request).check_health()
return Response(status_code=200)
except EngineDeadError:
return Response(status_code=503)
@router.get("/load")