After multiple model workers start working concurrently for the first time, requests will only be received by one of the workers.

I am using a server.controller to control 3 model_workers, which are placed on 3 GPUs, and then I opened 3 identical server.gradio_web_server and input the same question. The first time, all 3 gradio_web_server can output content at the same time. But when all the outputs are finished, the second time I send requests to all three gradio_web_server simultaneously, only one model_worker works (i.e., only one gradio_web_server has a streaming output), and when I check the GPU utilization, only one GPU is being used. Can anyone tell me what the reason for this is?
Is there anyone who has the same question?

我使用一个server.controller控制了3个model_worker，分别放置在3张GPU上，然后打开了3个相同的server.gradio_web_server，输入同一个问题，第一次，这3个gradio_web_server能同时输出内容，等到全部输出完毕后，第二次同时向这三个gradio_web_server发送请求，只会有一个model_worker工作（即只有一个gradio_web_server有流式输出），查看显卡利用率也仅仅只有一块GPU被使用，请问这是什么原因呢？
有任何朋友跟我有一样的疑问吗？

Reproduce the second-round request sequence with server.controller, three model_worker processes, and three server.gradio_web_server instances. Start by tracing request assignment and worker availability across those entry points; done means identifying why only one worker receives work and documenting or correcting the behavior with a verified reproduction.