FastChat
FastChat copied to clipboard
How deepseekcoder6.7b supports streaming output results
How deepseekcoder6.7b supports streaming output results?
Similar issue here using Qwen-7B-Chat. What's the proper way to use streaming mode in openai api? Streaming for this model works fine in gradio web server.
This PR introduces the feature, but the test code uses from fastchat import Client
, which does not exist.
Any advice? @baradm100
httpx.RemoteProtocolError: peer closed connection without sending complete message body (incomplete chunked read)