apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Trace]fix opentelemetry can not work in uvicorn (#2906)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* add opentelemetry

* add opentelemetry

* add opentelemetry on dequeue

* add opentelemetry on dequeue

* add opentelemetry on dequeue

* fix annotation

* fix annotation when add opentelemetry

* fix opentelemetry-instrumentation-fastapi

* fix pentelemetry-bootstrap

* fix opentelemetry can not work in uvicorn

* move conf to env

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
sg263
2025-07-17 23:16:45 +08:00
committed by GitHub
parent bbe2c5c968
commit e679567d59
3 changed files with 106 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -24,7 +24,7 @@ import zmq
from fastapi import FastAPI, Request
from fastapi.responses import JSONResponse, Response, StreamingResponse
from prometheus_client import CONTENT_TYPE_LATEST
from fastdeploy.metrics.trace_util import inject_to_metadata
from fastdeploy.metrics.trace_util import inject_to_metadata,instrument
from fastdeploy.engine.args_utils import EngineArgs
from fastdeploy.engine.engine import LLMEngine
@@ -141,6 +141,7 @@ async def lifespan(app: FastAPI):
app = FastAPI(lifespan=lifespan)
instrument(app)
# TODO 传递真实引擎值 通过pid 获取状态
@@ -397,11 +398,6 @@ def launch_controller_server():
"""Controller server running the sub thread"""
if args.controller_port < 0:
return
if not is_port_available(args.host, args.controller_port):
raise Exception(
f"The parameter `controller_port`:{args.controller_port} is already in use."
)
if not is_port_available(args.host, args.controller_port):
raise Exception(