david/flash-attention

mirrorاز https://github.com/Dao-AILab/flash-attention

نویسنده	SHA1 پیام	تاریخ
sclarkson	1feb711f46 Fix compilation with clang on ARM64 (#1285)	2 ماه پیش
Tri Dao	dff68c2b22 Add smoothing for CrossEntropyParallel, rename to CrossEntropyLoss	2 سال پیش
Tri Dao	7c9953815a Add fused cross entropy loss	2 سال پیش