report a problem about running gradio_demo.py slowly

[JerryFanFan]

When I executed gradio_demo.py, I noticed that it took an exceptionally long time without yielding any results. Upon inspecting the code, I found that there seems to be an issue with the execution of the submit_button_component.click in relation to the Gradio component.

When using queue=True（default）, Gradio handles requests in a new process, which prevents the CUDA context from being shared between processes, causing the GPU model inference to hang. Setting queue=False allows requests to be processed directly in the main process, avoiding this issue.

submit_button_component.click(
        fn=process,
       ......
        queue=False 
    )