david/flash-attention

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

Auteur	SHA1 Message	Date
Tri Dao	36587c01cb [LayerNorm] Update layer_norm_linear	il y a 9 mois
Tri Dao	bdcae547c7 [LayerNorm] Don't exit early in the backward pass (fix #781)	il y a 11 mois
Tri Dao	c9861a032d [LayerNorm] Initialize mean and rstd tensor using x.device	il y a 1 an
Tri Dao	f5b308e258 [LayerNorm] Rename layernorm.py -> layer_norm.py	il y a 1 an