lm-sys / lm-sys/FastChat

AttributeError: module 'torch.cuda' has no attribute 'OutOfMemoryError'

Open
#1,627 2 comments 2 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

When using the langchain-chatGLM project to run, the model does not report an error and can be used normally, but when it is changed to FastChat, the following error appears. What is the reason for this?

Environment
python=3.8.16,torch=1.12.1,
T4

model
chatGLM-6B-int4

Error
AttributeError: module 'torch.cuda' has no attribute 'OutOfMemoryError'
image

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

The payload names no source file or test. Start by reproducing FastChat with Python 3.8.16, PyTorch 1.12.1, a T4, and the chatGLM-6B-int4 model, then trace where torch.cuda.OutOfMemoryError is accessed. Done means the compatibility cause is confirmed and the affected behavior has a tested resolution.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
ai, backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.