lm-sys / lm-sys/FastChat

How to specify which GPU to run the model in background mode on?

Open
#2,181 8 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

Previously, by using - gpus 0 or 1, the model could be run on the specified gpu. But after upgrading the latest code for fastchat and reinstalling the environment components, gpus no longer works. May I ask how to solve it?

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

Start by reproducing background-mode model serving with the reported -gpus 0 or 1 option in the current FastChat environment, then compare it with the previously working behavior. Done means the requested GPU is selected reliably or the supported invocation and limitation are documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.