[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-70930":3},{"id":4,"name":5,"fullName":6,"owner":5,"repo":5,"description":7,"homepage":8,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":16,"stars30d":16,"stars90d":15,"forks30d":15,"starsTrendScore":17,"compositeScore":18,"rankGlobal":9,"rankLanguage":9,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":9,"pushedAt":9,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":15,"starSnapshotCount":15,"syncStatus":27,"lastSyncTime":28,"discoverSource":29},70930,"fauxpilot","fauxpilot\u002Ffauxpilot","FauxPilot - an open-source alternative to GitHub Copilot server","",null,"Python",14732,645,118,59,0,1,3,43.43,"MIT License",false,"main",true,[],"2026-06-12 02:02:45","\n# FauxPilot\n\nThis is an attempt to build a locally hosted alternative to [GitHub Copilot](https:\u002F\u002Fcopilot.github.com\u002F). It uses the [SalesForce CodeGen](https:\u002F\u002Fgithub.com\u002Fsalesforce\u002FCodeGen) models inside of NVIDIA's [Triton Inference Server](https:\u002F\u002Fdeveloper.nvidia.com\u002Fnvidia-triton-inference-server) with the [FasterTransformer backend](https:\u002F\u002Fgithub.com\u002Ftriton-inference-server\u002Ffastertransformer_backend\u002F).\n\n\u003Cp align=\"right\">\n  \u003Cimg width=\"50%\" align=\"right\" src=\".\u002Fimg\u002Ffauxpilot.png\">\n\u003C\u002Fp>\n\n## Prerequisites\n\nYou'll need:\n\n* Docker\n* `docker compose` >= 1.28\n* An NVIDIA GPU with Compute Capability >= 6.0 and enough VRAM to run the model you want.\n* [`nvidia-docker`](https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fnvidia-docker)\n* `curl` and `zstd` for downloading and unpacking the models.\n\nNote 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.\n\n\n## Support and Warranty\n\nlmao\n\nOkay, fine, we now have some minimal information on [the wiki](https:\u002F\u002Fgithub.com\u002Fmoyix\u002Ffauxpilot\u002Fwiki) and a [discussion forum](https:\u002F\u002Fgithub.com\u002Fmoyix\u002Ffauxpilot\u002Fdiscussions) where you can ask questions. Still no formal support or warranty though!\n\n\n\n## Setup\n\nThis section describes how to install a Fauxpilot server and clients.\n\n### Setting up a FauxPilot Server\n\nRun the setup script to choose a model to use. This will download the model from [Huggingface\u002FMoyix](https:\u002F\u002Fhuggingface.co\u002FMoyix) in GPT-J format and then convert it for use with FasterTransformer.\n\nPlease refer to [How to set-up a FauxPilot server](documentation\u002Fserver.md).\n\n\n### Client configuration for FauxPilot\n\nWe 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.\n\nPlease refer to [How to set-up a client](documentation\u002Fclient.md).\n\n\n## Terminology\n * API: Application Programming Interface\n * CC: Compute Capability\n * CUDA: Compute Unified Device Architecture\n * FT: Faster Transformer\n * JSON: JavaScript Object Notation \n * gRPC: Remote Procedure call by Google\n * GPT-J: A transformer model trained using Ben Wang's Mesh Transformer JAX \n * REST: REpresentational State Transfer\n","FauxPilot 是一个开源的本地托管替代方案，旨在模仿 GitHub Copilot 服务器的功能。它利用了SalesForce CodeGen模型，并通过NVIDIA Triton Inference Server和FasterTransformer后端进行部署，以提供代码补全和建议服务。项目支持多种客户端配置方式，包括OpenAI API、Copilot插件以及REST API等，使得用户可以根据自身需求灵活接入。适合那些希望在本地环境中使用类似GitHub Copilot功能但又担心数据安全或寻求更低成本解决方案的开发者与团队使用。",2,"2026-06-11 03:35:01","high_star"]