xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-28 08:58:42 +08:00
Code Issues Packages Projects Releases Wiki Activity

[1/N] API Server (Remove Proxy) (#11529)

Browse Source
This commit is contained in:
Robert Shaw 2024-12-26 18:03:43 -05:00 committed by GitHub
parent b85a977822
commit 720b10fdc6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 17 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
vllm/entrypoints/openai/api_server.py
View File

@ -585,12 +585,18 @@ def build_app(args: Namespace) -> FastAPI:
status_code=401)
return await call_next(request)
@app.middleware("http")
async def add_request_id(request: Request, call_next):
request_id = request.headers.get("X-Request-Id") or uuid.uuid4().hex
response = await call_next(request)
response.headers["X-Request-Id"] = request_id
return response
if args.enable_request_id_headers:
logger.warning(
"CAUTION: Enabling X-Request-Id headers in the API Server. "
"This can harm performance at high QPS.")
@app.middleware("http")
async def add_request_id(request: Request, call_next):
request_id = request.headers.get(
"X-Request-Id") or uuid.uuid4().hex
response = await call_next(request)
response.headers["X-Request-Id"] = request_id
return response
for middleware in args.middleware:
module_path, object_name = middleware.rsplit(".", 1)

6
vllm/entrypoints/openai/cli_args.py
View File

@ -196,7 +196,11 @@ def make_arg_parser(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
action="store_true",
help="If specified, will run the OpenAI frontend server in the same "
"process as the model serving engine.")
parser.add_argument(
"--enable-request-id-headers",
action="store_true",
help="If specified, API server will add X-Request-Id header to "
"responses. Caution: this hurts performance at high QPS.")
parser.add_argument(
"--enable-auto-tool-choice",
action="store_true",