david/flash-attention

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

Autor	SHA1 Mensagem	Data
Tri Dao	36587c01cb [LayerNorm] Update layer_norm_linear	há 9 meses atrás
Tri Dao	bdcae547c7 [LayerNorm] Don't exit early in the backward pass (fix #781)	há 11 meses atrás
Tri Dao	c9861a032d [LayerNorm] Initialize mean and rstd tensor using x.device	há 1 ano atrás
Tri Dao	f5b308e258 [LayerNorm] Rename layernorm.py -> layer_norm.py	há 1 ano atrás