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 17, 01:45 UTC
[Frontend] Add --log-level option to api server (#4377)
Norman Mu committed
Apr 25, 2024 at 22:36 UTC
2f30e7c72fca61c8225654880ee1ef89cad1690c
1 file changed
+2
-1
vllm/entrypoints/api_server.py
+2
-1
@@ -100,6 +100,7 @@ if __name__ == "__main__":
100
type=str,
101
default=None,
102
help="FastAPI root_path when app is behind a path based routing proxy")
103
+ parser.add_argument("--log-level", type=str, default="debug")
104
parser = AsyncEngineArgs.add_cli_args(parser)
105
args = parser.parse_args()
106
engine_args = AsyncEngineArgs.from_cli_args(args)
@@ -110,7 +111,7 @@ if __name__ == "__main__":
111
uvicorn.run(app,
112
host=args.host,
113
port=args.port,
113
- log_level="debug",
114
+ log_level=args.log_level,
115
timeout_keep_alive=TIMEOUT_KEEP_ALIVE,
116
ssl_keyfile=args.ssl_keyfile,
117
ssl_certfile=args.ssl_certfile,