david/flash-attention

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

Autore	SHA1 Messaggio	Data
Chirag Jain	50896ec574 Make nvcc threads configurable via environment variable (#885)	9 mesi fa
Tri Dao	dc08ea1c33 Support H100 for other CUDA extensions	1 anno fa
Tri Dao	7c9953815a Add fused cross entropy loss	2 anni fa