InternLM / InternLM/Tutorial

lmdeploy教程疑问 - KV Cache量化和W4A16量化怎么叠加?

Open
#376 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
2k
Forks
1.5k
PR merge metrics
No merged PRs in 30d

Description

[lmdeploy教程量化部分](https://github.com/InternLM/tutorial/blob/main/lmdeploy/lmdeploy.md#3-%E6%A8%A1%E5%9E%8B%E9%87%8F%E5%8C%96) 分别介绍了如何做KV Cache量化和W4A16量化,两者结果都得到turbomind格式的模型。
但怎么把这两者结合起来?比如在KV Cache量化的结果上做W4A16量化。
`lmdeploy lite calibrate`和`lmdeploy lite auto_awq`都𣎴接受turbomind格式的模型,该如何去叠加?

另外,如果想把量化后的模型和别人共享,怎么把turbomind格式的转换成hugging face格式的?

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.