david/flash-attention: flash-attention from https://github.com/Dao-AILab/flash-attention @ fa3-kvcache-gqa

зеркало из https://github.com/Dao-AILab/flash-attention

Tri Dao 8c20cfef49 [Rotary] Support qkv block layout from GQA		3 месяцев назад
..
__init__.py	ece539abd6 Add __init__.py files to subdirectories for installation	2 лет назад
patch_embed.py	f1a73d0740 Run isort and black on python files	1 год назад
rotary.py	8c20cfef49 [Rotary] Support qkv block layout from GQA	3 месяцев назад