ARMOR通过矩阵分解实现高效2:4稀疏化，显著提升大模型压缩后的性能。
ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
- 将权重矩阵分解为稀疏核心与低开销块对角包装层，动态优化误差校正。
- 在Llama和Qwen模型上实现比现有方法更低的困惑度与更高任务准确率。
- 适合追求高精度压缩的大模型部署场景，兼顾速度与内存节省。
大语言模型（LLMs）因计算与内存需求巨大，部署面临严峻挑战。半结构化剪枝，尤其是2:4稀疏模式，为硬件加速提供了可行路径，但现有方法常导致显著性能下降。为此，我们提出ARMOR（自适应矩阵分解表示）：一种一次性后训练剪枝算法。不同于直接剪枝权重，ARMOR将每个权重矩阵分解为一个2:4稀疏核心，外加两个低开销的块对角矩阵作为前后变换误差校正器，提供更强灵活性以保持模型质量。稀疏核心与块对角包装层通过块坐标下降算法选择，以最小化层级代理损失。理论上证明该优化可收敛至代理损失不超过当前最优方法的解。在Llama（Touvron et al., 2023; Dubey et al., 2024）和Qwen（Yang et al., 2025）模型族上的实验表明，ARMOR在多种下游任务与困惑度评估中均显著优于现有2:4剪枝方法。其在保持2:4剪枝带来的推理加速与大幅内存减少的同时，实现了更优的压缩-精度权衡。
原文摘要 · Abstract (English)
Large language models (LLMs) present significant deployment challenges due to their immense computational and memory requirements. While semi-structured pruning, particularly 2:4 sparsity, offers a path to practical hardware acceleration, existing methods often incur substantial performance degradation. To bridge this gap, we introduce ARMOR: (Adaptive Representation with Matrix-factORization), a novel one-shot post-training pruning algorithm. Instead of directly pruning weights, ARMOR factorizes each weight matrix into a 2:4 sparse core wrapped by two low-overhead, block diagonal matrices. These wrappers act as efficient pre and post-transformation error correctors, offering greater flexibility to preserve model quality compared to conventional 2:4 pruning techniques. The sparse core and block diagonal wrappers are chosen through a block coordinate descent algorithm that minimizes a layer-wise proxy loss. We theoretically prove this optimization is guaranteed to converge to a solution with a proxy loss less than or equal to state-of-the-art pruning algorithms. Experiments on Llama (Touvron et al., 2023; Dubey et al., 2024) and Qwen (Yang et al., 2025) model families demonstrate that ARMOR consistently and significantly outperforms state-of-the-art 2:4 pruning methods across a wide range of downstream tasks and perplexity evaluations. ARMOR achieves this superior performance while retaining the inference speedups and substantial memory usage reductions of 2:4 pruning, establishing a more effective trade-off between model compression and task accuracy
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。