david/flash-attention

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

Autore	SHA1 Messaggio	Data
Avelina9X	c94cd09744 Updated missing docstrings for args and returns in bert_padding.py (#795)	10 mesi fa
Su Zhu	8f6f48d8a8 add unpad_input_for_concatenated_sequences (#499)	1 anno fa
Tri Dao	f1a73d0740 Run isort and black on python files	1 anno fa
Antoine Adam	4e38df059e remove numpy dependency	2 anni fa
Tri Dao	6cc7342575 Support index_first_axis with more than 2 dimensions	2 anni fa
Tri Dao	5a61cb7729 Rename src -> flash_attn	2 anni fa