david/flash-attention

Mirror von https://github.com/Dao-AILab/flash-attention

Autor	SHA1 Nachricht	Datum
Tri Dao	fc2fd95a18 Renable FP8 kernels	vor 1 Monat
Tri Dao	64d92bce53 Split PagedKV into separate .cu files to speed up compilation	vor 1 Monat
Tri Dao	586ba914bb Move fwd tile size to a separate file	vor 1 Monat
Tri Dao	018b9af683 Move .cu files to instantiations, use generate_kernels.py	vor 1 Monat