@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 1066cbd152
Fork 0

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)