lm-sys/FastChat

View on GitHub

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Stars: 39.5k
Forks: 4.8k
Open beginner issues: 2
Indexed issues: 899

Dominant language: Python
License: Apache-2.0
Last GitHub push: Jun 2, 2025
Latest indexed: Sep 19, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: good first issue help wanted
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

899 open issues indexed

Print SEED Value for each response [Feature request] Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

lm-sys/FastChat#3215 · Opened Apr 2, 2024
Better device_map and max_memory for loading vicuna model Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

lm-sys/FastChat#3214 · Opened Apr 2, 2024
JSON decode error Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3212 · 1 comment · Opened Apr 2, 2024
如何进行多卡多机，有没有详细教程 Open

Difficulty 5/5 Over a week Newbie friendliness 15/100

lm-sys/FastChat#3209 · Opened Mar 31, 2024
[embedding model & connect with Langchain] "POST /v1/embeddings HTTP/1.1" 500 Internal Server Error Open

Difficulty 3/5 1-2 days Newbie friendliness 25/100

lm-sys/FastChat#3205 · Opened Mar 29, 2024
Add `--max-model-len` param and description to `serve.vllm_worker`? Open

Difficulty 2/5 1-3 hours Newbie friendliness 45/100

lm-sys/FastChat#3203 · 1 comment · Opened Mar 29, 2024
Support package-data for llm_judge Open

Difficulty 2/5 1-3 hours Newbie friendliness 45/100

lm-sys/FastChat#3199 · Opened Mar 27, 2024
【微调模型调用有问题】Using a fine-tuned model for a Q&A with the output in English was not the answer I was looking for Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3197 · Opened Mar 26, 2024
Looking forward to adding support for Qwen1.5 Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

lm-sys/FastChat#3196 · 4 comments · 2 reactions · Opened Mar 26, 2024
python -m fastchat.serve.model_worker --model-path /data1/workspaces/llama2/Llama-2-7b-chat-hf --host 0.0.0.0 Open

Difficulty 4/5 3-5 days Newbie friendliness 15/100

lm-sys/FastChat#3195 · 6 comments · Opened Mar 26, 2024
What is the fastest token generation speed for Vicuna-13B? Open

Difficulty 4/5 3-5 days Newbie friendliness 20/100

lm-sys/FastChat#3192 · Opened Mar 24, 2024
RuntimeError when running qa_browser.py Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

lm-sys/FastChat#3190 · 1 reaction · Opened Mar 23, 2024
better way of processing the Content Warning Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

lm-sys/FastChat#3189 · 2 comments · Opened Mar 23, 2024
chatgpt template `get_prompt` got error ValueError: Invalid style: None Open

Difficulty 3/5 1-2 days Newbie friendliness 25/100

lm-sys/FastChat#3188 · 1 comment · 1 reaction · Opened Mar 23, 2024
How much budget is needed to call gpt4 api judge a model on mt-bench? Open

Difficulty 5/5 Over a week Newbie friendliness 15/100

lm-sys/FastChat#3182 · 1 comment · Opened Mar 21, 2024
is FastChat suppport Embedding model such as gte-base? Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3181 · 3 comments · 1 reaction · Opened Mar 21, 2024
Is FastChat not support M3E-BASE？ Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3180 · 1 comment · Opened Mar 21, 2024
run qwen-1.5-4b-chat with vllm worker failed: max seq len (32768) is larger than the maximum number of tokens Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3177 · 1 comment · Opened Mar 20, 2024
run "python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --device npu" Generated Answer Generates Other Languages or Strings Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3174 · Opened Mar 20, 2024
After QLoRA finetuning, the inference output repeat the instruction over and over again Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3171 · Opened Mar 19, 2024
[Leaderboard] Wrong Link for GPT-4-0125-Preview Open

Difficulty 2/5 1-3 hours Newbie friendliness 35/100

lm-sys/FastChat#3169 · Opened Mar 19, 2024
Grok-1 Model Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

lm-sys/FastChat#3167 · 5 reactions · Opened Mar 18, 2024
Developers, could you please add support for the Telechat model in FastChat? Open

Difficulty 5/5 Over a week Newbie friendliness 15/100

lm-sys/FastChat#3165 · Opened Mar 18, 2024
The review has become too strict Open

Difficulty 4/5 3-5 days Newbie friendliness 20/100

lm-sys/FastChat#3162 · 3 comments · Opened Mar 16, 2024
update chatbot_arena_conversations dataset Open

Difficulty 4/5 3-5 days Newbie friendliness 20/100

lm-sys/FastChat#3161 · 1 reaction · Opened Mar 16, 2024
if len(chunk["choices"]) == 0: KeyError: 'choices' Open

Difficulty 3/5 1-2 days Newbie friendliness 15/100

lm-sys/FastChat#3160 · Opened Mar 16, 2024
Unreachable code in `get_worker_address` Open

Difficulty 3/5 1-2 days Newbie friendliness 30/100

lm-sys/FastChat#3155 · 1 comment · Opened Mar 14, 2024
HTML injection of the web prompt: possible safety issue? Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3154 · Opened Mar 14, 2024
RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'RuntimeError: "addmm_impl_cpu_" not implemented for 'Half' Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3153 · Opened Mar 14, 2024
using --device=xpu Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3152 · 1 comment · Opened Mar 14, 2024
Can fastchat support multiple model calls? Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

lm-sys/FastChat#3151 · Opened Mar 14, 2024
Document diverged OpenAI API Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

lm-sys/FastChat#3147 · 3 comments · Opened Mar 13, 2024
error Inference on for long-context text Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

lm-sys/FastChat#3144 · 4 comments · Opened Mar 12, 2024
`fastchat.serve.controller` stops working after a while Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3142 · Opened Mar 11, 2024
Is Codellama-70B-Instruct-hf now supported? Open

Difficulty 3/5 1-2 days Newbie friendliness 25/100

lm-sys/FastChat#3135 · 1 reaction · Opened Mar 9, 2024
SGLang worker does not expose embeddings. Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

lm-sys/FastChat#3132 · Opened Mar 8, 2024
这个项目是停止更新了么？很久没看到新的更新 Open

Difficulty 5/5 Over a week Newbie friendliness 10/100

lm-sys/FastChat#3128 · 2 comments · Opened Mar 6, 2024
How do I submit my API endpoint to you? Open

Difficulty 1/5 Under an hour Newbie friendliness 25/100

lm-sys/FastChat#3127 · 1 comment · Opened Mar 5, 2024
why not have log in conversion history？ hope add log info Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

lm-sys/FastChat#3126 · 1 comment · Opened Mar 4, 2024
Exllama output continues conversation Open

Difficulty 3/5 1-2 days Newbie friendliness 38/100

lm-sys/FastChat#3125 · Opened Mar 4, 2024
No module named 'fastchat.protocol' Open

Difficulty 3/5 1-2 days Newbie friendliness 32/100

lm-sys/FastChat#3124 · 3 comments · Opened Mar 4, 2024
Automatic truncation input messages by model max content length Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

lm-sys/FastChat#3123 · Opened Mar 4, 2024
sglang_worker doesn't work for GPTQ models Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

lm-sys/FastChat#3122 · Opened Mar 3, 2024
issues trying to run FastChat with '--device mps' option Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3120 · Opened Mar 3, 2024
Whether to support tools invocation Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

lm-sys/FastChat#3118 · 2 reactions · Opened Mar 2, 2024
Agreement Computation - Have you considered using Krippendorff's Alpha? Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

lm-sys/FastChat#3115 · Opened Mar 1, 2024
不太理解？我想用到自己部署的开源模型的tokenier，应该怎么用接口怎么调用呢？ Open

Difficulty 3/5 1-2 days Newbie friendliness 25/100

lm-sys/FastChat#3114 · Opened Mar 1, 2024
About special tokens Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

lm-sys/FastChat#3113 · 2 comments · Opened Mar 1, 2024
Need to support Qwen1.5-72B-Chat 32k token? Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

lm-sys/FastChat#3112 · 2 comments · Opened Mar 1, 2024
gradio_web_server_multi fails Open

Difficulty 2/5 1-3 hours Newbie friendliness 48/100

lm-sys/FastChat#3111 · 1 reaction · Opened Feb 29, 2024

lm-sys/FastChat

Get new issues in your inbox