Feature: Start LLM service with fastchat.
Closed this issue · 0 comments
IRONICBo commented
Checklist
- I've searched for similar issues and couldn't find anything matching
- I've discussed this feature request in the OpenIMSDK Slack and got positive feedback
Is this feature request related to a problem?
❎ No
Problem Description
Enable multi llm models loader with fastchat frame.
Solution Description
Use fastchat.serve.controller
, fastchat.serve.model_worker
, fastchat.serve.openai_api_server
instead.
Ref: https://github.com/lm-sys/FastChat/blob/main/docs/langchain_integration.md
Benefits
Enhance system.
Potential Drawbacks
No response
Additional Information
No response