{"full_name":"lm-sys/FastChat","owner":"lm-sys","name":"FastChat","url":"https://github.com/lm-sys/FastChat","description":"An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.","homepage":"","topics":[],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/126381704?v=4","created_at":"2023-03-19T00:18:02Z","pushed_at":"2026-05-01T00:25:53Z","metrics":{"stars":39548,"forks":4770,"watchers":355,"issues":1990,"prs":1295,"releases":14,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":0},"growth":{"day":{"stars":1,"forks":0,"base_day":"2026-11-09"}},"history":{"dates":["2026-11-09","2026-11-10"],"stars":[39547,39548],"forks":[4770,4770],"watchers":[355,355],"issues_open":[null,null],"prs_open":[null,null]},"boards":{},"same_owner":[{"full_name":"lm-sys/RouteLLM","name":"RouteLLM","boards":{}}],"issues":[{"number":1264,"title":"Chat Arena version of fastchat-t5-3b-v1.0 provides more refined answers than standard Huggingface model.","comments":26,"created_at":"2023-05-15T14:23:43Z"},{"number":1741,"title":"NotImplementedError: Cannot copy out of meta tensor; no data!","comments":19,"created_at":"2023-06-20T05:48:05Z"},{"number":1200,"title":"torch.distributed.elastic.multiprocessing.errors.ChildFailedError:","comments":17,"created_at":"2023-05-11T09:01:50Z"},{"number":2726,"title":"chatglm3 error: why are there multiple <|assistant|> <|user|> tags in the generated datas?","comments":15,"created_at":"2023-11-23T11:52:35Z"},{"number":646,"title":"fastchat-t5-3b-v1.0 on macOS?","comments":15,"created_at":"2023-04-29T23:00:14Z"},{"number":1475,"title":"openai.error.APIError: Invalid response object from API: '{\"object\":\"error\",\"message\":\"\",\"code\":50001}' (HTTP response code was 500)","comments":14,"created_at":"2023-05-24T21:52:10Z"},{"number":591,"title":"How to run train_lora.py","comments":14,"created_at":"2023-04-25T06:55:13Z"},{"number":3266,"title":"Finetuning Llama3-8B fails due to lack of a PAD token in new tokenizer","comments":13,"created_at":"2024-04-21T01:17:24Z"}],"discussions":[],"latest_release":{"name":"Release v0.2.36","tag":"v0.2.36","published_at":"2024-02-11T15:40:27Z","body":"## Highlights\r\n- Added SGLang worker for vision language models, lower latency and higher throughput https://github.com/lm-sys/FastChat/pull/2928\r\n- Vision langauge WebUI https://github.com/lm-sys/FastChat/pull/2960\r\n- OpenAI-compatible API server now supports image input https://github.com/lm-sys/FastChat/pull/2928\r\n- Added LightLLM worker for higher throughput https://github.com/lm-sys/FastChat/blob/main/docs/lightllm_integration.md\r\n- Added Apple MLX worker https://github.com/lm-sys/FastChat/pull/2940\r\n\r\n## What's Changed\r\n* fix specify local path issue use model from www.modelscope.cn by @liuyhwangyh in https://github.com/lm-sys/FastChat/pull/2934\r\n* support openai embedding for topic clustering by @CodingWithTim in https://github.com/lm-sys/FastChat/pull/2729\r\n* Remove duplicate API endpoint by @surak in https://github.com/lm-sys/FastChat/pull/2949\r\n* Update Hermes Mixtral by @teknium1 in https://github.com/lm-sys/FastChat/pull/2938\r\n* Enablement of REST API Usage within Google Colab Free Tier by @ggcr in https://github.com/lm-sys/FastChat/pull/2940\r\n* Create a new worker implementation for Apple MLX by @aliasaria in https://github.com/lm-sys/FastChat/pull/2937\r\n* feat: support Model Yuan2.0, a new generation Fundamental Large Language Model developed by IEIT System by @cauwulixuan in https://github.com/lm-sys/FastChat/pull/2936\r\n* Fix the pooling method of BGE embedding model by @staoxiao in https://github.com/lm-sys/FastChat/pull/2926\r\n* SGLang Worker by @BabyChouSr in https://github.com/lm-sys/FastChat/pull/2928\r\n* Update mlx_worker to be async by @aliasaria in https://github.com/lm-sys/FastChat/pull/2958\r\n* Integrate LightLLM into serve worker by @zeyugao in https://github.com/lm-sys/FastChat/pull/2888\r\n* Copy button by @surak in https://github.com/lm-sys/FastChat/pull/2963\r\n* feat: train with template by @congchan in https://github.com/lm-sys/FastChat/pull/2951\r\n* fix content maybe a str by @zhouzaida in https://github.com/lm-sys/FastChat/pull/2968\r\n* Adding download folder information in README by @dheeraj-326 in https://github.com/lm-sys/FastChat/pull/2972\r\n* use cl100k_base as the default tiktoken encoding by @bjwswang in https://github.com/lm-sys/FastChat/pull/2974\r\n* Update README.md by @merrymercy in https://github.com/lm-sys/FastChat/pull/2975\r\n* Fix tokenizer for vllm worker by @Michaelvll in https://github.com/lm-sys/FastChat/pull/2984\r\n* update yuan2.0 generation by @wangpengfei1013 in https://github.com/lm-sys/FastChat/pull/2989\r\n* fix: tokenization mismatch when training with different templates by @congchan in https://github.com/lm-sys/FastChat/pull/2996\r\n* fix: inconsistent tokenization by llama tokenizer by @congchan in https://github.com/lm-sys/FastChat/pull/3006\r\n* Fix type hint for play_a_match_single by @MonkeyLeeT in https://github.com/lm-sys/FastChat/pull/3008\r\n* code update by @infwinston in https://github.com/lm-sys/FastChat/pull/2997\r\n* Update model_support.md by @infwinston in https://github.com/lm-sys/FastChat/pull/3016\r\n* Update lightllm_integration.md by @eltociear in https://github.com/lm-sys/FastChat/pull/3014\r\n* Upgrade gradio to 4.17 by @infwinston in https://github.com/lm-sys/FastChat/pull/3027\r\n* Update MLX integration to use new generate_step function signature by @aliasaria in https://github.com/lm-sys/FastChat/pull/3021\r\n* Update readme by @merrymercy in https://github.com/lm-sys/FastChat/pull/3028\r\n* Update gradio version in `pyproject.toml` and fix a bug by @merrymercy in https://github.com/lm-sys/FastChat/pull/3029\r\n* Update gradio demo and API model providers by @merrymercy in https://github.com/lm-sys/FastChat/pull/3030\r\n* Gradio Web Server for Multimodal Models by @BabyChouSr in https://github.com/lm-sys/FastChat/pull/2960\r\n* Migrate the gradio server to openai v1 by @merrymercy in https://github.com/lm-sys/FastChat/pull/3032\r\n* Update version to 0.2.36 by @merrymercy in https://github.com/lm-sys/FastChat/pull/3033\r\n\r\n## New Contributors\r\n* @teknium1 made their first contrib"},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}