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, 05:30 UTC
Remove deprecated parameter: concurrency_count (#2315)
Ronen Schaffer committed
Jan 3, 2024 at 19:56 UTC
1066cbd152fb7c9a096e914a10ce675a14796b92
1 file changed
+3
-3
examples/gradio_webserver.py
+3
-3
@@ -47,6 +47,6 @@ if __name__ == "__main__":
47
args = parser.parse_args()
48
49
demo = build_demo()
50
- demo.queue(concurrency_count=100).launch(server_name=args.host,
51
- server_port=args.port,
52
- share=True)
50
+ demo.queue().launch(server_name=args.host,
51
+ server_port=args.port,
52
+ share=True)