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 13, 00:45 UTC
Supress verbose logs from model_hosting_container_standards (#28949)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Nov 18, 2025 at 15:29 UTC
67745d189fd981ee824bde35666a3737a962c031
1 file changed
+4
vllm/entrypoints/openai/api_server.py
+4
@@ -5,6 +5,7 @@ import hashlib
5
import importlib
6
import inspect
7
import json
8
+import logging
9
import multiprocessing
10
import multiprocessing.forkserver as forkserver
11
import os
@@ -2020,6 +2021,9 @@ async def run_server(args, **uvicorn_kwargs) -> None:
2021
# Add process-specific prefix to stdout and stderr.
2022
decorate_logs("APIServer")
2023
2024
+ # Suppress verbose logs from model_hosting_container_standards
2025
+ logging.getLogger("model_hosting_container_standards").setLevel(logging.ERROR)
2026
+
2027
listen_address, sock = setup_server(args)
2028
await run_server_worker(listen_address, sock, args, **uvicorn_kwargs)
2029