2 results found Sort:

DefTruth
CUDA-Learn-Notes DefTruth
81
806
gpl-3.0
10
🎉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.
cuda gemm gemv rmsnorm softmax layernorm elementwise warp-reduce block-reduce cuda-kernels flash-attention cuda-programming flash-attention-2
Created 2022-12-17
110 commits to main branch, last one a day ago
Liu-xiandong
How_to_optimize_in_GPU Liu-xiandong
118
749
apache-2.0
12
This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sg...
hpc sgemm sgemv reduce elementwise gpu-acceleration high-performance-computing
Created 2021-10-17
58 commits to master branch, last one 11 months ago