github.com/lm-sys/FastChat issues | Ecosyste.ms: OpenCollective

Fix asymmetrical bootstrap error for style control.

CodingWithTim opened this pull request 4 months ago

Integrate vllm Error, TypeError: top_k must be an integer, got float

alanhsu777 opened this issue 4 months ago

Fix Style control Bootstrapping

CodingWithTim opened this pull request 4 months ago

Added NewYorker images back in

lisadunlap opened this pull request 4 months ago

sglang_work not working on sglang v0.2.13

exceedzhang opened this issue 4 months ago

is_blocking is bool

tp-nan opened this issue 4 months ago

Add load test

BabyChouSr opened this pull request 4 months ago

Add Style Control to Chatbot Arena Leaderboard 🔥

CodingWithTim opened this pull request 4 months ago

Update monitor_md.py

infwinston opened this pull request 4 months ago

Update preset images

lisadunlap opened this pull request 4 months ago

Update dataset_release.md

merrymercy opened this pull request 4 months ago

Version names for Command R/R+

sanderland opened this pull request 4 months ago

update queue_lens on generation ends.

lcw99 opened this pull request 4 months ago

Update vllm worker

BabyChouSr opened this pull request 4 months ago

Revert "Add max-model-len argument to vllm worker"

vikrantrathore opened this pull request 4 months ago

Support Bailing model

cuauty opened this issue 4 months ago

npu-910-glm4 Generated Answer Generates Other Languages or Strings

Demainlip opened this issue 4 months ago

插件使用process.env读取不到环境变量

blvyoucan opened this issue 4 months ago

After multiple model workers start working concurrently for the first time, requests will only be received by one of the workers.

PaulX1029 opened this issue 4 months ago

Enable vision arena across all tabs

BabyChouSr opened this pull request 4 months ago

fix the bugs when some parameters are empty

zjasper666 opened this pull request 4 months ago

Request to add [HODACHI/EZO-Humanities-9B-gemma-2-it] and [HODACHI/EZO-Common-9B-gemma-2-it] to Chatbot Arena

kazuya-hodatsu-336-1 opened this issue 4 months ago

`httpx.RemoteProtocolError: peer closed connection without sending complete message body (incomplete chunked read)`

DHaru85 opened this issue 4 months ago

AttributeError: 'GenerationConfig' object has no attribute '_eos_token_tensor'

Demainlip opened this issue 4 months ago

Store the image moderation and text moderation logs

BabyChouSr opened this pull request 4 months ago

removed a duplicate line

gpgg opened this pull request 4 months ago

Add Support for Loading Models in 4-bit Quantized Version (Fixes #1798)

02shanks opened this pull request 4 months ago

ERROR | stderr | ERROR: [Errno 99] error while attempting to bind on address ('::1', 21002, 0, 0): cannot assign requested address

LIUKAI0815 opened this issue 4 months ago

Llama3 Local Model

sven-123 opened this issue 4 months ago

不更新了吗？

a1015498799 opened this issue 4 months ago

⚔️ Arena (side-by-side) sometimes show one model as "rate-exceeded" while the other model keeps generating things.

yuxi-liu-wired opened this issue 4 months ago

How to modify URLs when using third-party API

ChangPingfirst opened this issue 4 months ago

【bug】KeyError: 'factor' when use Triplex

ForgetThatNight opened this issue 5 months ago

Update Bard connector to use gemini_api_stream_iter

asadovsky opened this pull request 5 months ago

Slower throughput with openai_server

tacacs1101-debug opened this issue 5 months ago

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

nstl-zyb opened this issue 5 months ago

Survey only

lisadunlap opened this pull request 5 months ago

New leaderboard

lisadunlap opened this pull request 5 months ago

Does the current project provide an interface for calculating the number of tokens for testing inference performance?

tensorflowt opened this issue 5 months ago

Merged duplicate `GeminiAdapter` class definitions

KangmoonSeo opened this pull request 5 months ago

Duplicate GeminiAdapter class definition found

KangmoonSeo opened this issue 5 months ago

add survey link

lisadunlap opened this pull request 5 months ago

Update monitor.py

infwinston opened this pull request 5 months ago

Does the FastChat framework support multiple NPU reasoning? I changed the value of num_gpus to 4, but after he loads the model, it will not distribute it equally to each graphics card.

xunmenglt opened this issue 5 months ago

npu 910B run fastchat + baichuan-13B: DefaultCPUAllocator: can't allocate memory

GuIIWen opened this issue 5 months ago

Arena hard auto leaderboard UI

CodingWithTim opened this pull request 5 months ago

support musa backend for MooreThreads

caizhi-mt opened this pull request 5 months ago

No permission to push to the branch

caizhi-mt opened this issue 5 months ago

Does the FastChat model support gemma2-27b it?

zhouyuustc opened this issue 5 months ago

Does MT-Bench gen_model_answer.py accept adapter weights (adapter_config.json) file as model path?

RitikParkar opened this issue 5 months ago

Llama 3.1 - Wrong context length reported in `/token_check` endpoint

PyroGenesis opened this issue 5 months ago

Add max-model-len argument to vllm worker

aliasaria opened this pull request 5 months ago

Support Mistral-7B-Instruct-v0.3

WxxShirley opened this issue 5 months ago

How to finetune mistral-7b with fastchat?

Jerry-hyl opened this issue 5 months ago

Error in Gemma 2 using model_worker (probably an error in conversation.py)

vikrantrathore opened this issue 5 months ago

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。

6277668 opened this issue 5 months ago

"Cannot read properties of undefined (reading 'originalname')

yuchubill opened this issue 5 months ago

fix: get_prompt goes wrong for Llama-2

yangjunx21 opened this pull request 5 months ago

Model worker with Nvidia NIM?

surak opened this issue 5 months ago

Flag preset images

BabyChouSr opened this pull request 5 months ago

Dealing with filtering user queries where they ask models to give their names

fjiangAI opened this issue 5 months ago

Must provide either the `api_version` argument or the `OPENAI_API_VERSION` environment variable

Bob199511 opened this issue 6 months ago

Openai_api_server Error: 400 status code (no body)

GianlucaDeStefano opened this issue 6 months ago

[Suggest] When to support Codestral

lance-maxwell opened this issue 6 months ago

added leaderboard for arena hard auto

connorchenn opened this pull request 6 months ago

vllm context_len fix

baoyf4244 opened this pull request 6 months ago

Merge messages error

bluechanel opened this pull request 6 months ago

add a performant worker dash-infer which is specifically optimized for CPU environments

yejunjin opened this pull request 6 months ago

Chatbot Arena Category Classification Script

CodingWithTim opened this pull request 6 months ago

Explicitly support GritLM

janEbert opened this pull request 6 months ago

turkish data added

emrecanacikgoz opened this pull request 6 months ago

[Bug]: Garbled Tokens appears in vllm generation result every time change to new LLM model

Jason-csc opened this issue 6 months ago

Error reported when deploying DeepSeek-Coder-V2-Lite-Chat with latest Fastchat

xierbut opened this issue 6 months ago

Error reported when deploying DeepSeek-Coder-V2-Lite-Chat with latest Fastchat

xierbut opened this issue 6 months ago

How can we get our custom API-based model's rank in the leaderboard?

FelixZheng1 opened this issue 6 months ago

Update monitor

infwinston opened this pull request 6 months ago

Merge operation & multimodal arena

infwinston opened this pull request 6 months ago

"FAILED: cpu_adam.so " when I use LoRA to train the model😭😭😭

Mucalinda2436 opened this issue 6 months ago

Add logprobs support with OpenAI API chat completions

BastienLeGuellec opened this pull request 6 months ago

Make logprobs accessible for chat completions with the OpenAI API

BastienLeGuellec opened this pull request 6 months ago

chatglm3-6b-32k generate abnormal output like <|user|> and <|assistant|>

zotM opened this issue 6 months ago

[Chatbot Arena] Add GLM-4 variants: AirX, Air and Flash

EwoutH opened this issue 6 months ago

/v1/chat/completions Does not have a corresponding abort interface？

xieyongshuai opened this issue 6 months ago

SHARE NOT WORKING

Satvik-jain opened this issue 6 months ago

Can GPTCache be used in FastChat?

3togo opened this issue 6 months ago

Add Claude sonnet 3.5

cyounkins opened this pull request 6 months ago

Add Claude 3.5 Sonnet

cyounkins opened this issue 6 months ago

Use Reka Python SDK and add script for benchmarking and add send_btn

BabyChouSr opened this pull request 6 months ago

Add GPT-J 6B

upintheairsheep opened this issue 6 months ago

glm4 Churn out

pingyuan2016 opened this issue 6 months ago

ascend NPU how to Multiple NPUs

50785397 opened this issue 6 months ago

unable to communicate with mistral models deployed in EC2 by using gradio_webserver API

kambalaashok4 opened this issue 6 months ago

how to serve Gradio app on the cloud and run inference locally

ouhenio opened this issue 6 months ago

Refactor image classes, fix resizing, support SVG images, unify text and vision arena

BabyChouSr opened this pull request 6 months ago

[Feat Request] Adding 72b/110b llava to multimodal chatbot areana

Luodian opened this issue 6 months ago

Fix the issue of semaphore unreleased due to internal exception

StephenZKCurry opened this pull request 6 months ago

Added llm-judge support for GPT-4o

danielwetzel opened this pull request 6 months ago

LLM + knowledge Graph

plyu3 opened this issue 6 months ago

adapting glm-4

litterGuy opened this pull request 6 months ago

Update model_adapter.py

KnightLancelot opened this pull request 6 months ago