david/flash-attention

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

Autor	SHA1 Mensagem	Data
Tri Dao	eb33e587e9 [LayerNorm] Rename x1 -> residual	há 1 ano atrás
Tri Dao	6738d9477d [LayerNorm] Implement RMS Norm	há 1 ano atrás
Tri Dao	5db330519a [LayerNorm] Support taking subset of input or subset of output	há 2 anos atrás
Tri Dao	ae137ed17a [LayerNorm] Fuse LayerScale	há 2 anos atrás
Tri Dao	8c6609ae1a [LayerNorm] Support all dimensions up to 6k (if divisible by 8)	há 2 anos atrás
Tri Dao	fa6d1ce44f Add fused_dense and dropout_add_layernorm CUDA extensions	há 2 anos atrás