lm-sys / lm-sys/FastChat

Speed comparison with https://huggingface.co/chat/

Open
#2,037 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

The speed difference is astounding compared to https://huggingface.co/chat/ when running llama2-70b-chat.

I wonder what I am doing wrong. I have A100 gpus, but the maximum on a single node are 4, so I can't run fastchat there to compare.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are named. Start by reproducing the llama2-70b-chat speed comparison with the available A100 setup, then document the configuration and identify what explains the difference; done means a verified explanation or a concrete FastChat issue to fix.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
ai, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.