david/flash-attention

mirror de https://github.com/Dao-AILab/flash-attention

Autor	SHA1 Mensagem	Data
Tri Dao	7f5d73a162 Add env var to disable specific hdim	há 1 mês atrás
Tri Dao	3e5d77a102 Group instantiations for different hdims together	há 1 mês atrás
Tri Dao	fc2fd95a18 Renable FP8 kernels	há 2 meses atrás
Tri Dao	64d92bce53 Split PagedKV into separate .cu files to speed up compilation	há 2 meses atrás
Tri Dao	586ba914bb Move fwd tile size to a separate file	há 2 meses atrás
Tri Dao	018b9af683 Move .cu files to instantiations, use generate_kernels.py	há 2 meses atrás