lm-sys / lm-sys/FastChat

issues trying to run FastChat with '--device mps' option

Open
#3,120 0 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

hi

i'm having issues running FastChat on an Apple Silicon M1 machine with 16G of RAM.
i'm using the `--device mps --load-8bit` options but i keep getting a runtime error.

`RuntimeERror: Userspecified an unsupported autocast device_type 'mps'`

Why is that?
I'm running it within conda with python 3.12.2
when i try
`import torch
torch.backends.mps.is_avilable()`
the results is `True`
which hopefully confirms that my libraries are installed correctly...

I manage to get the inital prompt loaded, but the moment i type a question. the runtime error is thrown.

What am i doing wrong?

Thanks

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

Reproduce the reported FastChat invocation with `--device mps --load-8bit` on Apple Silicon using Python 3.12.2, and capture the full runtime traceback. Start by tracing the device and autocast handling that produces the unsupported `mps` error; done means the cause is identified and the supported behavior or required compatibility change is documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
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.