david/flash-attention

kopia lustrzana https://github.com/Dao-AILab/flash-attention

Autor	SHA1 Wiadomość	Data
Tri Dao	0e8c46ae08 Run isort and black on test files	1 rok temu
Tri Dao	93383bd55b [TP] Implement TensorParallel without sequence parallel	1 rok temu
Tri Dao	1e712ea8b0 Implement TensorParallel for MHA	2 lat temu