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 6, 14:30 UTC
[openapi] remove redundant exception stack trace[4/N] (#37157)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Ning Xie committed
Mar 17, 2026 at 23:06 UTC
c9e50962567df7e509591185ba71fb0bfa9f0392
1 file changed
+1
-1
vllm/entrypoints/openai/server_utils.py
+1
-1
@@ -371,7 +371,7 @@ async def generation_error_handler(req: Request, exc: GenerationError):
371
372
async def exception_handler(req: Request, exc: Exception):
373
if req.app.state.args.log_error_stack:
374
- logger.exception(
374
+ logger.error(
375
"Exception caught. Request id: %s",
376
req.state.request_metadata.request_id
377
if hasattr(req.state, "request_metadata")