NIOT: A Novel Inference Optimization of Transformers on Modern CPUs

Zining Zhang 0001, Yao Chen, Bingsheng He, Zhenjie Zhang. NIOT: A Novel Inference Optimization of Transformers on Modern CPUs. IEEE Trans. Parallel Distrib. Syst., 34(6):1982-1995, June 2023. [doi]

@article{ZhangCHZ23,
  title = {NIOT: A Novel Inference Optimization of Transformers on Modern CPUs},
  author = {Zining Zhang 0001 and Yao Chen and Bingsheng He and Zhenjie Zhang},
  year = {2023},
  month = {June},
  doi = {10.1109/TPDS.2023.3269530},
  url = {https://doi.org/10.1109/TPDS.2023.3269530},
  researchr = {https://researchr.org/publication/ZhangCHZ23},
  cites = {0},
  citedby = {0},
  journal = {IEEE Trans. Parallel Distrib. Syst.},
  volume = {34},
  number = {6},
  pages = {1982-1995},
}