DefTruth / CUDA-Learn-Notes

🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.

Date Created 2022-12-17 (about a year ago)

Commits 93 (last one 12 days ago)

Stargazers 625 (15 this week)

Watchers 7 (0 this week)

Forks 68

License gpl-3.0

Ranking

RepositoryStats indexes 523,840 repositories, of these DefTruth/CUDA-Learn-Notes is ranked #71,792 (86th percentile) for total stargazers, and #256,773 for total watchers. Github reports the primary language for this repository as Cuda, for repositories using this language it is ranked #35/272.

DefTruth/CUDA-Learn-Notes is also tagged with popular topics, for these it's ranked: cuda (#124/571)

Other Information

DefTruth/CUDA-Learn-Notes has Github issues enabled, there are 2 open issues and 3 closed issues.

There have been 3 releases, the latest one was published on 2024-03-25 (2 months ago) with the name v0.3 flash_attn-1 fwd f32.

Homepage URL: https://github.com/DefTruth/cuda-learn-notes

All Topics

cuda gemm gemv rmsnorm softmax layernorm elementwise warp-reduce block-reduce cuda-kernels flash-attention cuda-programming flash-attention-2

Star History

Github stargazers over time

Watcher History

Github watchers over time, collection started in '23

Recent Commit History

93 commits on the default branch (main) since jan '22

Yearly Commits

Commits to the default branch (main) per year

Issue History

Languages

The primary language is Cuda but there's also others...

updated: 2024-05-31 @ 08:02pm, id: 579300230 / R_kgDOIodrhg