InternLM / InternLM/lmdeploy

[Bug] int4 awq kernel

Open
#498 0 comments 0 reactions 1 assignee Claimed by @lzhangzz 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

我在研究awq,发现int4量化的kernel中可能有一些bug。
- 首先,kernel计算有随机性,每次logits结果略有差异
- 通过 saveNpy 保存了中间结果,发现有的shape的gemm可能计算有问题,其中某几行的输出不正确,与llm-awq repo中的结果以及fp16 fake compute的计算结果不同(并且每次运算不一样,可能随机性也是来自这里)。(llama-7b-ffn-up-proj)

### Reproduction

按照文档运行llama-7b的awq量化

### 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.