token-sparse-attention-long-context

【数据与研究】Dynamically select important tokens at the attention head level, performing dense attention only on selected tokens and scattering results back. Achieves 3.23x attention speedup at 128K context with 1% accuracy loss through layer-wise representation stability analysis.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准