david/flash-attention: flash-attention from https://github.com/Dao-AILab/flash-attention @ 4ead9bd7cc60e7b8b33c3af6b0b801488119f941

огледало од https://github.com/Dao-AILab/flash-attention

Chirag Jain 50896ec574 Make nvcc threads configurable via environment variable (#885)		пре 9 месеци
..
rotary.cpp	e45a46a5b7 [Rotary] Implement GPT-J style (interleaved) rotary	пре 1 година
rotary_cuda.cu	e45a46a5b7 [Rotary] Implement GPT-J style (interleaved) rotary	пре 1 година
setup.py	50896ec574 Make nvcc threads configurable via environment variable (#885)	пре 9 месеци