稀疏比特网络：1.58位大语言模型天然适配半结构化稀疏性

摘要

半结构化N:M稀疏性与低位量化（如1.58位BitNet）是提升大语言模型效率的两大前沿技术，但现有研究多孤立探讨二者。本文首次系统研究其交互作用，发现1.58位BitNet相比全精度模型天然具备更优的N:M稀疏兼容性。为此我们提出Sparse-BitNet——首个融合1.58位量化与动态N:M稀疏化的统一框架，并确保训练稳定性。在多种模型规模与训练机制（稀疏预训练、稠密到稀疏调度）下，1.58位BitNet在相同稀疏度下始终表现出更小的性能损失，且能承受更高结构化稀疏度而不发生精度崩溃。通过定制稀疏张量核心，Sparse-BitNet在训练与推理阶段均实现显著加速，最高达1.30倍。这些结果表明，极低位量化与半结构化N:M稀疏的结合是构建高效大语言模型的重要方向。代码已开源：https://github.com/AAzdi/Sparse-BitNet

English

Semi-structured N:M sparsity and low-bit quantization (e.g., 1.58-bit BitNet) are two promising approaches for improving the efficiency of large language models (LLMs), yet they have largely been studied in isolation. In this work, we investigate their interaction and show that 1.58-bit BitNet is naturally more compatible with N:M sparsity than full-precision models. To study this effect, we propose Sparse-BitNet, a unified framework that jointly applies 1.58-bit quantization and dynamic N:M sparsification while ensuring stable training for the first time. Across multiple model scales and training regimes (sparse pretraining and dense-to-sparse schedules), 1.58-bit BitNet consistently exhibits smaller performance degradation than full-precision baselines at the same sparsity levels and can tolerate higher structured sparsity before accuracy collapse. Moreover, using our custom sparse tensor core, Sparse-BitNet achieves substantial speedups in both training and inference, reaching up to 1.30X. These results highlight that combining extremely low-bit quantization with semi-structured N:M sparsity is a promising direction for efficient LLMs. Code available at https://github.com/AAzdi/Sparse-BitNet

稀疏比特网络：1.58位大语言模型天然适配半结构化稀疏性

Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity

摘要

Support