系统梳理量化训练的理论与实践，揭示不同目标下的差异与优化方向。
A Target-Centric Survey of Quantization-Aware Training
- 按目标分类梳理量化训练方法，分析误差特性与格式差异。
- 总结量化训练评估范式，指出优化与部署中的关键挑战。
- 适合关注模型压缩与高效推理的研究者与工程师。
大语言模型的快速发展带来了巨大的内存开销和计算需求。量化感知训练（QAT）通过在训练中显式模拟量化效应，成为缓解这一问题的有力方案，可生成低比特模型并在精度上接近全精度模型。本文从目标导向视角出发，系统回顾现有QAT方法，构建目标中心化分类体系，分析不同目标下误差特性、数值格式及策略可迁移性的差异。进一步总结了QAT的评估范式，讨论了优化与部署中的挑战，并展望未来研究方向。
原文摘要 · Abstract (English)
The rapid development of LLMs incurs prohibitive memory footprints and intensive computational demands. Quantization-Aware Training (QAT) techniques have emerged as a promising solution to address these challenges by explicitly simulating quantization effects during model training, yielding low-bit models that achieve accuracy comparable to their full-precision counterparts. In this work, we provide a target-centric survey of QAT, aimed at clarifying both its theoretical foundations and its evolving implementation landscape. We systematically review existing QAT methods through a target-centric taxonomy and synthesize cross-target differences in error characteristics, numerical formats, and strategy transferability. We further summarize QAT evaluation paradigms and discuss challenges in optimization and deployment, outlining potential directions for future research.
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。