cs.LGNov 19, 2026

HiSA: Sparsifying the Hidden Dimension of RoPE Attention in LLMs

Authors: Ambroise Borbely, Mathieu Salzmann, Olivier Verscheure

Organizations: EPFL, Switzerland · Swiss Data Science Center, EPFL and ETH Zurich, Switzerland

Abstract

Attention in large language models (LLMs) scores every query against every key with a full dot product. We investigate whether this dot product must be computed completely for attention to be effective. We propose Hidden Sparse Attention (HiSA), which keeps the query and key projections intact but only computes a partial dot product, following a static, parameter-free rule set by the token positions: attention becomes sparse in the hidden (feature) dimension, an axis much less explored than token sparsity, rather than over tokens as in almost all sparse attention methods. Based on the structure of rotary position embeddings (RoPE), we decompose keys and queries into parts which can be omitted when computing attention. By training LLMs from scratch with HiSA, we find that this partial dot product does not hurt but improves performance compared with the complete product while computing only about a third of the query-key products. During inference HiSA improves decoding speed and shrinks memory footprint. We also extend HiSA to FlashAttention-3 kernels for training and inference. Finally, we motivate our approach by showing that dense attention learns to suppress the attention score parts that HiSA drops. Code is available at https://github.com/ambroise-b/hisa.

Figures & tables

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate Attention

    Sep 27, 2026Kunming Shao, Jierun Chen, Yanli Wang +4Self-AttentionLLM Inference Acceleration

  2. Sparse Attention Is Matrix Approximation, Not Choosing from a Bag of Values

    Oct 7, 2026Fang Wan, Xufeng Liu, Fan Li +1Sparse AttentionEfficient Attention

  3. More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding

    Oct 3, 2026Noam Elata, Itay Lamprecht, Mikey Shechter +3LLM Inference AccelerationSparse Attention