InftyAI/llmlite

Issues

• test issue

  #62 opened 6 months ago by kerthcet
  8

• Support fall back across several providers

  #60 opened 6 months ago by kerthcet
  11

• Support counting tokens

  #59 opened 6 months ago by kerthcet
  1

• Support deepspeed-fastgen as another backend

  #57 opened a year ago by kerthcet
  0

• Support Baichuan2 Model

  #34 opened a year ago by kerthcet
  1

• vLLM not working as expected with ChatGLM2

  #55 opened a year ago by kerthcet
  0

• Support Stream output

  #52 opened a year ago by kerthcet
  0

• Support loading different adapter

  #51 opened a year ago by kerthcet
  0

• Support vLLM as the backend

  #32 opened a year ago by kerthcet
  2

• Support for Baichuan LLM

  #15 opened a year ago by kerthcet
  0

• Support serving via HTTP/RPC server

  #40 opened a year ago by kerthcet
  0

• Support serving fine-tuning layers easily

  #39 opened a year ago by kerthcet
  0

• Integration with langchain

  #38 opened a year ago by kerthcet
  0

• Support quantization

  #37 opened a year ago by kerthcet
  0

• support text-generation-inference

  #35 opened a year ago by kerthcet
  0

• Add codeLlama example

  #33 opened a year ago by kerthcet
  0

• Support system_prompt can be empty

  #31 opened a year ago by kerthcet
  0

• recognize model

  #30 opened a year ago by Jerry-Kon
  3

• Upload ChatLLM to PyPi

  #5 opened a year ago by kerthcet
  1

• Support for codeLlama

  #27 opened a year ago by kerthcet
  0

• Add support to ChatGPT API

  #6 opened a year ago by kerthcet
  0

• name

  #10 opened a year ago by Jerry-Kon
  2

• Support for StableLM

  #11 opened a year ago by kerthcet
  0

• Add support to Falcon LLM

  #8 opened a year ago by kerthcet
  0

• Add support to Claude-2 LLM

  #7 opened a year ago by kerthcet
  0

• Add test framework via github action

  #4 opened a year ago by kerthcet
  0