https://github.com/fauxpilot/fauxpilot

FauxPilot - an open-source alternative to GitHub Copilot server
https://github.com/fauxpilot/fauxpilot

Last synced: 25 days ago
JSON representation

FauxPilot - an open-source alternative to GitHub Copilot server

• Host: GitHub
• URL: https://github.com/fauxpilot/fauxpilot
• Owner: fauxpilot
• License: mit
• Created: 2022-08-03T02:14:22.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-04-09T08:42:23.000Z (7 months ago)
• Last Synced: 2024-10-11T06:04:25.110Z (28 days ago)
• Language: Python
• Homepage:
• Size: 2.9 MB
• Stars: 14,566
• Watchers: 123
• Forks: 619
• Open Issues: 63
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Codeowners: .github/CODEOWNERS

Awesome Lists containing this project

• awesome-github-copilot - Faux Pilot
• awesome-ai-coding - Fauxpilot
• awesome-coding-assistants - FauxPilot - hosted) (Uncategorized / Uncategorized)
• awesome-llmops - fauxpilot - source alternative to GitHub Copilot server |  | (Code AI / Vector search)
• awesome-repositories - fauxpilot/fauxpilot - FauxPilot - an open-source alternative to GitHub Copilot server (Python)
• awesome-ai4code - FauxPilot
• awesome-github-star - fauxpilot - an open-source alternative to GitHub Copilot server | fauxpilot | 13187 | (Python)
• awesome-privacy - Fauxpilot - an open-source,local alternative to GitHub Copilot server (Artificial Intelligence / Android Launcher)
• awesome-code-ai - FauxPilot
• fucking-awesome-privacy - Fauxpilot - an open-source,local alternative to GitHub Copilot server (Artificial Intelligence / Android Launcher)
• StarryDivineSky - fauxpilot/fauxpilot
• my-awesome - fauxpilot/fauxpilot - 04 star:14.6k fork:0.6k FauxPilot - an open-source alternative to GitHub Copilot server (Python)
• AiTreasureBox - fauxpilot/fauxpilot - 11-02_14587_-1](https://img.shields.io/github/stars/fauxpilot/fauxpilot.svg) | An open-source GitHub Copilot server | (Repos)

README

        

# FauxPilot

This is an attempt to build a locally hosted alternative to [GitHub Copilot](https://copilot.github.com/). It uses the [SalesForce CodeGen](https://github.com/salesforce/CodeGen) models inside of NVIDIA's [Triton Inference Server](https://developer.nvidia.com/nvidia-triton-inference-server) with the [FasterTransformer backend](https://github.com/triton-inference-server/fastertransformer_backend/).



  



## Prerequisites

You'll need:

* Docker

* `docker compose` >= 1.28

* An NVIDIA GPU with Compute Capability >= 6.0 and enough VRAM to run the model you want.

* [`nvidia-docker`](https://github.com/NVIDIA/nvidia-docker)

* `curl` and `zstd` for downloading and unpacking the models.

Note that the VRAM requirements listed by `setup.sh` are *total* -- if you have multiple GPUs, you can split the model across them. So, if you have two NVIDIA RTX 3080 GPUs, you *should* be able to run the 6B model by putting half on each GPU.

## Support and Warranty

lmao

Okay, fine, we now have some minimal information on [the wiki](https://github.com/moyix/fauxpilot/wiki) and a [discussion forum](https://github.com/moyix/fauxpilot/discussions) where you can ask questions. Still no formal support or warranty though!

## Setup

This section describes how to install a Fauxpilot server and clients.

### Setting up a FauxPilot Server

Run the setup script to choose a model to use. This will download the model from [Huggingface/Moyix](https://huggingface.co/Moyix) in GPT-J format and then convert it for use with FasterTransformer.

Please refer to [How to set-up a FauxPilot server](documentation/server.md).

### Client configuration for FauxPilot

We offer some ways to connect to FauxPilot Server. For example, you can create a client by how to open the Openai API, Copilot Plugin, REST API.

Please refer to [How to set-up a client](documentation/client.md).

## Terminology

 * API: Application Programming Interface

 * CC: Compute Capability

 * CUDA: Compute Unified Device Architecture

 * FT: Faster Transformer

 * JSON: JavaScript Object Notation 

 * gRPC: Remote Procedure call by Google

 * GPT-J: A transformer model trained using Ben Wang's Mesh Transformer JAX 

 * REST: REpresentational State Transfer