This paper provides a comprehensive overview of the principles, challenges, and methodologies associated with quantizing large-scale neural network models. As neural networks have evolved towards larger and more complex architectures to address increasingly sophisticated tasks, the computational and energy costs have escalated significantly. We explore the necessity and impact of model size growth, highlighting the performance benefits as well as the computational challenges and environmental considerations. The core focus is on model quantization as a fundamental approach to mitigate these challenges by reducing model size and improving efficiency without substantially compromising accuracy. We delve into various quantization techniques, including both post-training quantization (PTQ) and quantization-aware training (QAT), and analyze several state-of-the-art algorithms such as LLM-QAT, PEQA(L4Q), ZeroQuant, SmoothQuant, and others. Through comparative analysis, we examine how these methods address issues like outliers, importance weighting, and activation quantization, ultimately contributing to more sustainable and accessible deployment of large-scale models.

翻译：本文全面综述了大规模神经网络模型量化相关的原理、挑战与方法论。随着神经网络为应对日益复杂的任务而演变为更大、更复杂的架构，其计算与能耗成本显著攀升。我们探讨了模型规模增长的必要性与影响，既强调了其性能优势，也剖析了随之而来的计算挑战与环境考量。本文的核心聚焦于模型量化这一基础性方法，旨在通过缩减模型规模、提升效率来缓解上述挑战，同时不显著损害模型精度。我们深入探讨了多种量化技术，包括训练后量化（PTQ）与量化感知训练（QAT），并分析了LLM-QAT、PEQA(L4Q)、ZeroQuant、SmoothQuant等前沿算法。通过对比分析，我们研究了这些方法如何应对异常值、重要性加权及激活量化等问题，最终推动大规模模型实现更可持续、更易获取的部署。