@article{acceleratingdeeplearningmodelinferenceon,
  title = {Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtime},
  author = {Saad Ashfaq and MohammadHossein AskariHemmat and Sudhakar Sah and Ehsan Saboori and Olivier Mastropietro and Alexander Hoffman},
  year = {2022},
  eprint = {2207.08820},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2207.08820v1},
}