Closed xieyongshuai closed 3 months ago
In the application I developed to request fastchat /v1/chat/completions interface, how to implement the flow abort return, and really let the big model free resources
How is this completed? I would like to have a "stop" button on the web server.
In the application I developed to request fastchat /v1/chat/completions interface, how to implement the flow abort return, and really let the big model free resources