apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-09-26 20:41:53 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Update api_server.py

Browse Source
This commit is contained in:
Jiang-Jia-Jun
2025-09-15 21:31:33 +08:00
committed by GitHub
parent 03b3d6175d
commit a04365a0c7
1 changed files with 1 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
fastdeploy/entrypoints/openai/api_server.py
View File

@@ -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)