@article{gwqgradientawareweightquantizationfor,
  title = {GWQ: Gradient-Aware Weight Quantization for Large Language Models},
  author = {Yihua Shao and Siyu Liang and Zijian Ling and Minxi Yan and Haiyang Liu and Siyu Chen and Ziyang Yan and Chenyu Zhang and Haotong Qin and Michele Magno and Yang Yang and Zhen Lei and Yan Wang and Jingcai Guo and Ling Shao and Hao Tang},
  year = {2024},
  eprint = {2411.00850},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.00850v2},
}