From a04365a0c7b4f36e525f8b1319503ad1f76bbf51 Mon Sep 17 00:00:00 2001 From: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> Date: Mon, 15 Sep 2025 21:31:33 +0800 Subject: [PATCH] Update api_server.py --- fastdeploy/entrypoints/openai/api_server.py | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fastdeploy/entrypoints/openai/api_server.py b/fastdeploy/entrypoints/openai/api_server.py index 0417e2cb8..40227d0a0 100644 --- a/fastdeploy/entrypoints/openai/api_server.py +++ b/fastdeploy/entrypoints/openai/api_server.py @@ -70,7 +70,7 @@ from fastdeploy.utils import ( parser = FlexibleArgumentParser() parser.add_argument("--port", default=8000, type=int, help="port to the http server") parser.add_argument("--host", default="0.0.0.0", type=str, help="host to the http server") -parser.add_argument("--workers", default=None, type=int, help="number of workers") +parser.add_argument("--workers", default=1, type=int, help="number of workers") parser.add_argument("--metrics-port", default=8001, type=int, help="port for metrics server") parser.add_argument("--controller-port", default=-1, type=int, help="port for controller server") parser.add_argument( @@ -94,9 +94,6 @@ parser.add_argument( parser = EngineArgs.add_cli_args(parser) args = parser.parse_args() -if args.workers is None: - args.workers = max(min(int(args.max_num_seqs // 32), 8), 1) - console_logger.info(f"Number of api-server workers: {args.workers}.") args.model = retrive_model_from_server(args.model, args.revision)