← 研踪 PaperTrailarXiv: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
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 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
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 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 ↗