david/flash-attention

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

Autor	SHA1 Mensagem	Data
Tri Dao	43ab0b5205 Mention that some CUDA extensions have only been tested on A100s	há 2 anos atrás
Tri Dao	2e33fc8e36 Add GPT and ViT models	há 2 anos atrás
Tri Dao	fa6d1ce44f Add fused_dense and dropout_add_layernorm CUDA extensions	há 2 anos atrás