@article{efficientllminferenceoncpus,
  title = {Efficient LLM Inference on CPUs},
  author = {Haihao Shen and Hanwen Chang and Bo Dong and Yu Luo and Hengyu Meng},
  year = {2023},
  eprint = {2311.00502},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.00502v2},
}