@article{slimllmsaliencedrivenmixedprecision,
  title = {SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models},
  author = {Wei Huang and Haotong Qin and Yangdong Liu and Yawei Li and Xianglong Liu and Luca Benini and Michele Magno and Xiaojuan Qi},
  year = {2024},
  eprint = {2405.14917},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.14917v1},
}