djmaze / tabbyAPI

An OAI compatible exllamav2 API that's both lightweight and fast

TabbyAPI

Note

Need help? Join the Discord Server and get the Tabby role. Please be nice when asking questions.

A FastAPI based application that allows for generating text using an LLM (large language model) using the Exllamav2 backend

Disclaimer

This API is still in the alpha phase. There may be bugs and changes down the line. Please be aware that you might need to reinstall dependencies if needed.

Help Wanted

Please check the issues page for issues that contributors can help on. We appreciate all contributions. Please read the contributions section for more details about issues and pull requests.

If you want to add samplers, add them in the exllamav2 library and then link them to tabbyAPI.

Getting Started

Read the Wiki for more information. It contains user-facing documentation for installation, configuration, sampling, API usage, and so much more.

Supported Model Types

TabbyAPI uses Exllamav2 as a powerful and fast backend for model inference, loading, etc. Therefore, the following types of models are supported:

• Exl2 (Highly recommended)

• GPTQ

• FP16 (using Exllamav2's loader)

Alternative Loaders/Backends

If you want to use a different model type than the ones listed above, here are some alternative backends with their own APIs:

• GGUF + GGML - KoboldCPP

• AWQ - Aphrodite Engine

• Text Generation WebUI

Contributing

If you have issues with the project:

• Describe the issues in detail

• If you have a feature request, please indicate it as such.

If you have a Pull Request

• Describe the pull request in detail, what, and why you are changing something

Developers and Permissions

Creators/Developers:

• kingbri

• Splice86

• Turboderp