DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models

DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models Wenjing Ke author Zhe Li author Dong Li author Lu Tian author Emad Barsoum author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track Franck Dernoncourt editor Daniel Preoţiuc-Pietro editor Anastasia Shimorina editor Association for Computational Linguistics Miami, Florida, US conference publication ke-etal-2024-dl 10.18653/v1/2024.emnlp-industry.10 https://aclanthology.org/2024.emnlp-industry.10/ 2024-11 113 119