Flare Fast Low Rank Attention

Implement low-rank attention routing using encode-decode factorization to achieve linear-time complexity on long sequences while maintaining compatibility with optimized attention kernels.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit c12282176f

Frequently asked questions

npx get-skill add adu2021/flare-fast-low-rank-attention