Skip to content

Conversation

@scbz4learning
Copy link

image image

最 Naive 版本的.
想移植marlin, 但是时间不够了

HONOR_CODE.md
REFERENCE.md

很多优化可以做
最主要的是应该做融合算子, 不然先反量化再gemm, 两次设备主机之间通信, 开销太大.
算子本身可以更优化, 但是框架本身提供的AWQ中注释来自英伟达官方, 好像也摸不清语法, 有待测试.

@scbz4learning scbz4learning requested a review from a team January 11, 2026 15:49
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant