Morph MORPH
SIGN IN SIGN UP
tejas / flash-attention

Fast and memory-efficient exact attention

0 0 208 Python

[Cute,Bwd,Sm100] All compute warps wait for lse_barrier

T
Tri Dao committed
d101fa73c6a8ccb4e0b95eb2aea77d1dfc1ad39e
Parent: 12e1c04