InternLM / InternLM/lmdeploy

[Bug] 微调后的 qwen-vl-chat的模型,使用提供的方法量化成 INT4,显存占用没有下降

Open
#2,028 0 comments 0 reactions 1 assignee Claimed by @lvhan028 View on GitHub
Dominant language
Python
Stars
8.1k
Forks
748
Avg merge
6d 2h
Merged PRs (30d)
54

Description

### Checklist

- [X] 1. I have searched related issues but cannot get the expected help.
- [X] 2. The bug has not been fixed in the latest version.

### Describe the bug

微调后的 qwen-vl-chat的模型,使用提供的方法量化成 INT4,推理时显存占用没有下降 , 未量化前占用 20G, 量化后占用 22G

### Reproduction

python38

### Environment

```Shell
cuda11.7 ATX4090 显卡 python38 torch2.2.2 lmdeploy 0.5.0
```

### Error traceback

_No response_

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.