david/flash-attention

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

Autor	SHA1 Mensagem	Data
Chirag Jain	50896ec574 Make nvcc threads configurable via environment variable (#885)	há 9 meses atrás
Tri Dao	dc08ea1c33 Support H100 for other CUDA extensions	há 1 ano atrás
Tri Dao	7c9953815a Add fused cross entropy loss	há 2 anos atrás