@article{illmefficientintegeronlyinferencefor,
  title = {I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models},
  author = {Xing Hu and Yuan Cheng and Dawei Yang and Zhihang Yuan and Jiangyong Yu and Chen Xu and Sifan Zhou},
  year = {2024},
  eprint = {2405.17849},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.17849v2},
}