A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 14:45 UTC
[Bugfix]Fix index out of range error in api server log (#16787)
Signed-off-by: WangErXiao <863579016@qq.com>
Robin committed
Apr 18, 2025 at 00:01 UTC
6211b92273f5935d66a704d77fade25202bad615
1 file changed
+2
-1
vllm/entrypoints/openai/api_server.py
+2
-1
@@ -881,7 +881,8 @@ def build_app(args: Namespace) -> FastAPI:
881
section async for section in response.body_iterator
882
]
883
response.body_iterator = iterate_in_threadpool(iter(response_body))
884
- logger.info("response_body={%s}", response_body[0].decode())
884
+ logger.info("response_body={%s}",
885
+ response_body[0].decode() if response_body else None)
886
return response
887
888
for middleware in args.middleware: