Sync from v0.13

This commit is contained in:
2026-01-19 10:38:50 +08:00
parent b2ef04d792
commit 5aef6c175a
3714 changed files with 854317 additions and 89342 deletions

View File

@@ -0,0 +1,33 @@
# 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)
def attach_router(app):
app.include_router(router)

View File

@@ -0,0 +1,45 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import prometheus_client
import regex as re
from fastapi import FastAPI, Response
from prometheus_client import make_asgi_app
from prometheus_fastapi_instrumentator import Instrumentator
from starlette.routing import Mount
from vllm.v1.metrics.prometheus import get_prometheus_registry
class PrometheusResponse(Response):
media_type = prometheus_client.CONTENT_TYPE_LATEST
def attach_router(app: FastAPI):
"""Mount prometheus metrics to a FastAPI app."""
registry = get_prometheus_registry()
# `response_class=PrometheusResponse` is needed to return an HTTP response
# with header "Content-Type: text/plain; version=0.0.4; charset=utf-8"
# instead of the default "application/json" which is incorrect.
# See https://github.com/trallnag/prometheus-fastapi-instrumentator/issues/163#issue-1296092364
Instrumentator(
excluded_handlers=[
"/metrics",
"/health",
"/load",
"/ping",
"/version",
"/server_info",
],
registry=registry,
).add().instrument(app).expose(app, response_class=PrometheusResponse)
# Add prometheus asgi middleware to route /metrics requests
metrics_route = Mount("/metrics", make_asgi_app(registry=registry))
# Workaround for 307 Redirect for /metrics
metrics_route.path_regex = re.compile("^/metrics(?P<path>.*)$")
app.routes.append(metrics_route)