david/flash-attention

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

Autore	SHA1 Messaggio	Data
Tri Dao	88173a1aaf [FusedDense] Support relu, rename FusedDenseGeluDense -> FusedMLP	1 anno fa
Tri Dao	43798966cf [Docs] Fix formatting	1 anno fa
Tri Dao	3c7cbfc195 [Docs] Mention that dropout_layer_norm supports all dims up to 6k	1 anno fa
Tri Dao	4a6eaa9f27 Update configs, add results	2 anni fa
Tri Dao	0bf5e50038 Release training code	2 anni fa