Quantization-Aware Training

Also known as QAT

Overview

Quantization-aware training (QAT) simulates low-precision arithmetic during training so models can learn to withstand rounding and clipping errors at deployment. Common approaches use straight-through estimators, learned or mixed-precision quantizers, progressive bit reduction, and teacher-guided distillation. The methods are applied to settings from ImageNet vision models and edge devices to large language models, where evaluations include accuracy, perplexity, reasoning, and real-device speed. A central challenge is balancing accuracy against bit width and hardware cost: results depend on the numerical format and deployment path, and low-precision training can become unstable or diverge from inference behavior.

Latest papers

CardsList

94 papers11 papers in the last four weeks, down 39% on the four weeks before. 0.1% of all new papers.

  1. End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost

    Aug 21, 2025Qitao Tan, Xiaoying Song, Ningxi Cheng +11On-Device Language Model Fine-TuningLLM Quantization

  2. GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers

    Jun 13, 2025Guang Liang, Xinyao Liu, Jianxin WuQuantization-Aware Training4-Bit Quantization

  3. FedHQ: Hybrid Runtime Quantization for Federated Learning

    May 17, 2025Zihao Zheng, Ziyao Wang, Jiawei Yang +7Federated LearningAdaptive Quantization

  4. TernaryLLM: Ternarized Large Language Model

    Jun 11, 2024Tianqi Chen, Zhe Li, Weixiang Xu +6LLM QuantizationTernary Quantization