A Target-Centric Survey of Quantization-Aware Training

MCML Authors

Hinrich Schütze

Prof. Dr.

Core PI

Computational Linguistics

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.

inproceedings SZW+26

---

EMNLP 2026

Conference on Empirical Methods in Natural Language Processing. Budapest, Hungary, Oct 24-29, 2026. To be published. Preprint available.

---

Authors

J. Song • M. Zhao • Z. Wang • Y. Liu • Q. Li • S. Feng • F. Ren • D. Wang • H. Schütze

---

Links

arXiv

---

Research Area

 B2 | Natural Language Processing