30 lines
778 B
Python
30 lines
778 B
Python
|
# SPDX-License-Identifier: Apache-2.0
|
||
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||
|
|
|
||
|
|
|
||
|
|
from fastapi import APIRouter, Request
|
||
|
|
from fastapi.responses import Response
|
||
|
|
|
||
|
|
from vllm.engine.protocol import EngineClient
|
||
|
|
from vllm.logger import init_logger
|
||
|
|
from vllm.v1.engine.exceptions import EngineDeadError
|
||
|
|
|
||
|
|
logger = init_logger(__name__)
|
||
|
|
|
||
|
|
|
||
|
|
router = APIRouter()
|
||
|
|
|
||
|
|
|
||
|
|
def engine_client(request: Request) -> EngineClient:
|
||
|
|
return request.app.state.engine_client
|
||
|
|
|
||
|
|
|
||
|
|
@router.get("/health", response_class=Response)
|
||
|
|
async def health(raw_request: Request) -> Response:
|
||
|
|
"""Health check."""
|
||
|
|
try:
|
||
|
|
await engine_client(raw_request).check_health()
|
||
|
|
return Response(status_code=200)
|
||
|
|
except EngineDeadError:
|
||
|
|
return Response(status_code=503)
|