deepseek-ai / deepseek-ai/DeepGEMM
fp8_wgrad_gemm Support unaligned n,k and gmem stride?
Open
- Dominant language
- Cuda
- Stars
- 7.8k
- Forks
- 1.3k
- Avg merge
- 3d 7h
- Merged PRs (30d)
- 3
Description
in this commit
https://github.com/deepseek-ai/DeepGEMM/commit/919f55be9c77afdd593a0207c4bb42d7d7b99023
I found that it can only pass when the stride(0) of tensor lhs and tensor rhs is aligned to 64.
I would like to know how you ensure the alignment requirement of stride(0)？
extremely grateful
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.