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

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

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