@article{inferenceperformanceoptimizationforlarge,
  title = {Inference Performance Optimization for Large Language Models on CPUs},
  author = {Pujiang He and Shan Zhou and Wenhuan Huang and Changqing Li and Duyi Wang and Bin Guo and Chen Meng and Sheng Gui and Weifei Yu and Yi Xie},
  year = {2024},
  eprint = {2407.07304},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.07304v1},
}