Abstract:Semi-structured sparsity provides a practical path to accelerate large language models (LLMs) with native hardware support, but post-training semi-structured pruning often suffers from substantial quality degradation due to strong structural coupling. Existing methods rely on large-scale sparse retraining to recover accuracy, resulting in high computational cost.
We propose SparseForge, a post-training framework that improves recovery efficiency by directly optimizing the sparsity mask rather than scaling up retraining tokens. SparseForge combines Hessian-aware importance estimation with progressive annealing of soft masks into hardware-executable structured sparsity, enabling stable and efficient sparse recovery. On LLaMA-2-7B under 2:4 sparsity, SparseForge achieves 57.27% average zero-shot accuracy with only $\textbf{5B}$ retraining tokens, surpassing the dense model's 56.43% accuracy and approaching the 57.52% result of a state-of-the-art method using $\textbf{40B}$ tokens. Such improvements on the accuracy-efficiency trade-off from SparseForge are shown to be consistent across model families.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.06402 [cs.LG] |
| (or arXiv:2605.06402v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.06402 arXiv-issued DOI via DataCite (pending registration) |
From: Chaofan Lin [view email]
[v1]
Thu, 7 May 2026 15:11:45 UTC (756 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。