跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20549 · v1

RoShift: Lazy Shift and Weight-aware Rotation for Activation Sparsity in LLM Inference

首次提交 2026-11-16 13:28
版本更新 2026-11-16 13:28
雷达观测 2026-11-17 13:07
arXiv ↗PDF ↗

摘要

Activation sparsity accelerates LLM decoding by skipping unnecessary weight reads and computation. However, SiLU-based LLMs exhibit little natural sparsity, and imposing high sparsity can substantially degrade accuracy. We propose RoShift, a training-free method that transforms activations into sparsity-friendly representations. RoShift introduces lazy shift, which recenters SiLU activation distributions around zero and defers correction to the end of the FFN to obtain additional sparsity. It also reduces sparsification-induced output error through rotation that jointly accounts for activation and weight information. By fusing the corrections required for shifting and rotation, RoShift translates these gains into decoding speedup. At 50% and 60% sparsity, RoShift improves average accuracy over TEAL by 1.60 and 3.29 percentage points, respectively, across five models. It achieves up to 1.72×1.72\times decoding speedup over the dense model on an RTX 5090 at 50% sparsity and yields a better accuracy-speedup Pareto frontier than TEAL. Code is available at https://github.com/hulahula3247/RoShift

作者备注:40 pages, 10 figures, including appendices

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-16 13:28 · 最新观测版本

RoShift: Lazy Shift and Weight-aware Rotation for Activation Sparsity in LLM Inference

Activation sparsity accelerates LLM decoding by skipping unnecessary weight reads and computation. However, SiLU-based LLMs exhibit little natural sparsity, and imposing high sparsity can substantially degrade accuracy. We propose RoShift, a training-free method that transforms activations into sparsity-friendly representations. RoShift introduces lazy shift, which recenters SiLU activation distributions around zero and defers correction to the end of the FFN to obtain additional sparsity. It also reduces sparsification-induced output error through rotation that jointly accounts for activation and weight information. By fusing the corrections required for shifting and rotation, RoShift translates these gains into decoding speedup. At 50% and 60% sparsity, RoShift improves average accuracy over TEAL by 1.60 and 3.29 percentage points, respectively, across five models. It achieves up to 1.72×1.72\times decoding speedup over the dense model on an RTX 5090 at 50% sparsity and yields a better accuracy-speedup Pareto frontier than TEAL. Code is available at https://github.com/hulahula3247/RoShift

查看此版本解读 →查看此版本原文 ↗