A Target-Centric Survey of Quantization-Aware Training

Jiamin Song; Mengjie Zhao; Zijing Wang; Yongkang Liu; Qian Li; Shi Feng; Feiliang Ren; Daling Wang

cs.LGAug 30, 2026

A Target-Centric Survey of Quantization-Aware Training

Authors: Jiamin Song, Mengjie Zhao, Zijing Wang, Yongkang Liu, Qian Li, Shi Feng, Feiliang Ren, Daling Wang, +1 more

Organizations: 1Northeastern University, China · 2Shandong University, China · 3CIS, LMU Munich; MCML, Germany

Abstract

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.

Explore similar work

LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
Date pendingHaoyu Wang, Xingyu Yu, Haiyan Zhao +2Large Language Model Quantization Quantization
Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin
Jun 8, 2026Hanyang Li, Jianhao Ma, Ying CuiWeight-Only Quantization
JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates
May 25, 2026Kai Yi, Vignesh Vivekraja, Harshit Khaitan +1Extreme Low-Bit Quantization Time-Step-Wise Learnable Surrogate Gradient Function

Date pending · cs.CLJ/K move · Enter open · S save

LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization

Haoyu Wang, Xingyu Yu, Haiyan Zhao, Fengxiang Wang+1

Quantization-aware training (QAT) is essential for extremely low-bit large language models (LLMs). Current QAT methods are mainly based on scalar quantization (SQ), which enables efficient optimization but suffers from severe performance degradation at 2-bit precision. On the other hand, vector quantization (VQ) provides substantially higher representational capacity, but its discrete codebook lookup prevents end-to-end training. We propose LC-QAT, a 2-bit weight-only VQ-QAT framework that represents quantized weights via a learned affine mapping over discrete vectors, which yields a high-quality PTQ initialization and enables fully differentiable end-to-end optimization without explicit codebook lookup in the training forward pass. This strong post-training initialization makes LC-QAT highly data-efficient. Experiments across diverse LLMs demonstrate that LC-QAT consistently outperforms state-of-the-art QAT methods while using only 0.1%--10% of the training data. Our results establish LC-QAT as a practical and scalable solution for extreme low-bit model deployment. Codes are publicly available at https://github.com/AI9Stars/UniSVQ.

Large Language Model Quantization Quantization Codebooks Small Language Models

Open paper Ask about it PDF

Abstract

Explore similar work

LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization

Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin

JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates