Dao-AILab
★ 25,216flash-attention
Fast and memory-efficient exact attention. FlashAttention This repository provides the official implementation of FlashAttention and FlashAttention-2 from the following papers.
HYSEN LABS DIRECTORY
Verified repositories, classifications and analysis from the Dao-AILab organization.
Fast and memory-efficient exact attention. FlashAttention This repository provides the official implementation of FlashAttention and FlashAttention-2 from the following papers.
A Quirky Assortment of CuTe Kernels
Accelerating MoE with IO and Tile-aware Optimizations