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

Possible wrong llama 3.1 conversation template in conversation.py Open

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

lm-sys/FastChat#3547 · 2 reactions · Opened Oct 6, 2024
How to implement weight decay towards the pre-trained model? Open

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

lm-sys/FastChat#3545 · Opened Oct 3, 2024
Learderboard category/filter by model size Open

Difficulty 5/5 Over a week Newbie friendliness 30/100

lm-sys/FastChat#3544 · Opened Sep 30, 2024
an issue for repeat a command Open

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

lm-sys/FastChat#3542 · Opened Sep 30, 2024
Easily break the justice of judgement by asking: who are you Open

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

lm-sys/FastChat#3539 · 1 comment · 2 reactions · Opened Sep 28, 2024
cốt truyện của những tác phẩm của tác giả thạch lam khác gì so với các tác giả khác Open

Difficulty 5/5 Over a week Newbie friendliness 1/100

lm-sys/FastChat#3538 · Opened Sep 26, 2024
Models registered via web ui --register file.json don't appear as available on openai server list Open

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

lm-sys/FastChat#3537 · 1 comment · Opened Sep 26, 2024
Llama 3.1 chat template has <|begin_of_text|> encoded twice Open

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

lm-sys/FastChat#3535 · Opened Sep 25, 2024
Hardcoded host localhost and port 9090 for a rate monitor Open

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

lm-sys/FastChat#3531 · 2 comments · Opened Sep 20, 2024
Running FastChat on GPTQ (and quantized) models Open

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

lm-sys/FastChat#3530 · Opened Sep 19, 2024
Inquire about adding a new language to the category section on the Arena Open

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

lm-sys/FastChat#3526 · Opened Sep 16, 2024
How to use best-of-N in MT-Bench Open

Difficulty 3/5 1-2 days Newbie friendliness 20/100

lm-sys/FastChat#3524 · Opened Sep 14, 2024
GPTQ models - are they deprecated? Open

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

lm-sys/FastChat#3520 · Opened Sep 5, 2024
$MODERATION$ YOUR INPUT VIOLATES OUR CONTENT MODERATION GUIDELINES. Open

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

lm-sys/FastChat#3512 · Opened Sep 1, 2024
Is the logprobs of fschat==0.2.36 supported now? Open

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

lm-sys/FastChat#3506 · 1 comment · Opened Aug 30, 2024
Why logistic regression is equivalent to Bradley-Terry model? Open

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

lm-sys/FastChat#3505 · 2 comments · 1 reaction · Opened Aug 30, 2024
Integrate vllm Error, TypeError: top_k must be an integer, got float Open

Difficulty 1/5 Under an hour Newbie friendliness 45/100

lm-sys/FastChat#3501 · 1 comment · Opened Aug 28, 2024
sglang_work not working on sglang v0.2.13 Open

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

lm-sys/FastChat#3498 · Opened Aug 27, 2024
Support Bailing LLM from ALIPAY Open

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

lm-sys/FastChat#3487 · 2 comments · Opened Aug 20, 2024
npu-910-glm4 Generated Answer Generates Other Languages or Strings Open

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

lm-sys/FastChat#3486 · 4 comments · Opened Aug 20, 2024
After multiple model workers start working concurrently for the first time, requests will only be received by one of the workers. Open

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

lm-sys/FastChat#3484 · 3 comments · Opened Aug 19, 2024
Request to add [HODACHI/EZO-Humanities-9B-gemma-2-it] and [HODACHI/EZO-Common-9B-gemma-2-it] to Chatbot Arena Open

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

lm-sys/FastChat#3481 · Opened Aug 16, 2024
`httpx.RemoteProtocolError: peer closed connection without sending complete message body (incomplete chunked read)` Open

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

lm-sys/FastChat#3480 · 1 comment · 3 reactions · Opened Aug 16, 2024
ERROR | stderr | ERROR: [Errno 99] error while attempting to bind on address ('::1', 21002, 0, 0): cannot assign requested address Open

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

lm-sys/FastChat#3475 · Opened Aug 13, 2024
Llama3 Local Model Open

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

lm-sys/FastChat#3474 · Opened Aug 13, 2024
不更新了吗？ Open

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

lm-sys/FastChat#3473 · 8 comments · Opened Aug 13, 2024
⚔️ Arena (side-by-side) sometimes show one model as "rate-exceeded" while the other model keeps generating things. Open

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

lm-sys/FastChat#3472 · Opened Aug 13, 2024
How to modify URLs when using third-party API Open

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

lm-sys/FastChat#3471 · Opened Aug 9, 2024
【bug】KeyError: 'factor' when use Triplex Open

Difficulty 3/5 1-2 days Newbie friendliness 58/100

lm-sys/FastChat#3470 · 4 comments · Opened Aug 8, 2024
Slower throughput with openai_server Open

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

lm-sys/FastChat#3468 · Opened Aug 6, 2024
When using sglang as the inference framework, if a word starting with "\n" appears in the stop parameter, the sglang will Missing '\n' during inference Open

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

lm-sys/FastChat#3467 · 4 comments · Opened Aug 6, 2024
Duplicate GeminiAdapter class definition found Open

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

lm-sys/FastChat#3462 · Opened Aug 3, 2024
npu 910B run fastchat + baichuan-13B: DefaultCPUAllocator: can't allocate memory Open

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

lm-sys/FastChat#3458 · Opened Aug 1, 2024
No permission to push to the branch Open

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

lm-sys/FastChat#3455 · Opened Jul 31, 2024
Does the FastChat model support gemma2-27b it? Open

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

lm-sys/FastChat#3454 · 4 comments · 3 reactions · Opened Jul 26, 2024
Does MT-Bench gen_model_answer.py accept adapter weights (adapter_config.json) file as model path? Open

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

lm-sys/FastChat#3453 · Opened Jul 25, 2024
Llama 3.1 - Wrong context length reported in `/token_check` endpoint Open

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

lm-sys/FastChat#3452 · Opened Jul 25, 2024
How to finetune mistral-7b with fastchat? Open

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

lm-sys/FastChat#3449 · 1 comment · 1 reaction · Opened Jul 22, 2024
Error in Gemma 2 using model_worker (probably an error in conversation.py) Open

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

lm-sys/FastChat#3448 · 5 comments · Opened Jul 22, 2024
请问是否有计划更新open_ai_server内容去兼容最新的API的输入tools、tool_choice和输出tool_calls。 Open

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

lm-sys/FastChat#3446 · 1 comment · 4 reactions · Opened Jul 18, 2024
"Cannot read properties of undefined (reading 'originalname') Open

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

lm-sys/FastChat#3445 · Opened Jul 17, 2024
Model worker with Nvidia NIM? Open

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

lm-sys/FastChat#3443 · 1 comment · Opened Jul 12, 2024
Dealing with filtering user queries where they ask models to give their names Open

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

lm-sys/FastChat#3441 · Opened Jul 10, 2024
Must provide either the `api_version` argument or the `OPENAI_API_VERSION` environment variable Open

Difficulty 3/5 1-2 days Newbie friendliness 20/100

lm-sys/FastChat#3440 · 1 comment · Opened Jul 9, 2024
Openai_api_server Error: 400 status code (no body) Open

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

lm-sys/FastChat#3439 · Opened Jul 7, 2024
[Suggest] When to support Codestral Open

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

lm-sys/FastChat#3438 · 1 comment · 1 reaction · Opened Jul 5, 2024
[Bug]: Garbled Tokens appears in vllm generation result every time change to new LLM model Open

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

lm-sys/FastChat#3430 · 1 comment · Opened Jul 2, 2024
Error reported when deploying DeepSeek-Coder-V2-Lite-Chat with latest Fastchat Open

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

lm-sys/FastChat#3429 · 1 comment · Opened Jul 2, 2024
How can we get our custom API-based model's rank in the leaderboard? Open

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

lm-sys/FastChat#3427 · Opened Jul 1, 2024
"FAILED: cpu_adam.so " when I use LoRA to train the model😭😭😭 Open

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

lm-sys/FastChat#3424 · 1 comment · Opened Jun 29, 2024

lm-sys/FastChat

Get new issues in your inbox