david/flash-attention: flash-attention from https://github.com/Dao-AILab/flash-attention @ 6b1d059eda21c1bd421f3d352786fca2cab61954

spogulis no https://github.com/Dao-AILab/flash-attention

sclarkson 1feb711f46 Fix compilation with clang on ARM64 (#1285)		1 mēnesi atpakaļ
..
rotary.cpp	1feb711f46 Fix compilation with clang on ARM64 (#1285)	1 mēnesi atpakaļ
rotary_cuda.cu	e45a46a5b7 [Rotary] Implement GPT-J style (interleaved) rotary	1 gadu atpakaļ
setup.py	50896ec574 Make nvcc threads configurable via environment variable (#885)	10 mēneši atpakaļ