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 14, 05:30 UTC
[Misc] update log level debug to warning when process port is used by (#24226)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io> Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
rongfu.leng committed
Sep 11, 2025 at 02:32 UTC
09e68bce34175c6e6e57c7efcf2d1db216f5e8dd
1 file changed
+1
-1
vllm/entrypoints/launcher.py
+1
-1
@@ -95,7 +95,7 @@ async def serve_http(app: FastAPI,
95
port = uvicorn_kwargs["port"]
96
process = find_process_using_port(port)
97
if process is not None:
98
- logger.debug(
98
+ logger.warning(
99
"port %s is used by process %s launched with command:\n%s",
100
port, process, " ".join(process.cmdline()))
101
logger.info("Shutting down FastAPI HTTP server.")