proxy.golang.org : github.com/DefTruth/cuda-learn-note
đ CUDA Learn Notes with PyTorch: fp32ăfp16/bf16ăfp8/int8ăflash_attnăsgemmăsgemvăwarp/block reduceădot prodăelementwiseăsoftmaxălayernormărmsnormăhist etc.
Registry
-
Source
- Documentation
- JSON
purl: pkg:golang/github.com/%21def%21truth/cuda-learn-note
Keywords:
block-reduce
, cuda
, cuda-programming
, elementwise
, flash-attention
, flash-attention-2
, flash-attention-3
, gemm
, gemv
, layernorm
, pytorch
, rmsnorm
, softmax
, triton
, warp-reduce
License: GPL-3.0
Latest release: 15 days ago
First release: about 1 year ago
Stars: 1,151 on GitHub
Forks: 116 on GitHub
See more repository details: repos.ecosyste.ms
Last synced: 15 days ago
github.com/deftruth/cuda-learn-note v3.0.15+incompatible
đ CUDA Learn Notes with PyTorch: fp32ăfp16/bf16ăfp8/int8ăflash_attnăsgemmăsgemvăwarp/block reduce...49 versions - Latest release: 13 days ago - 1,151 stars on GitHub