@article{adeeplearninginferenceschemebasedon, title = {A Deep Learning Inference Scheme Based on Pipelined Matrix Multiplication Acceleration Design and Non-uniform Quantization}, author = {Yuyang Zhang and Dik Hin Leung and Min Guo and Yijia Xiao and Haoyue Liu and Yunfei Li and Jiyuan Zhang and Guan Wang and Zhen Chen}, year = {2021}, eprint = {2110.04861}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2110.04861v1}, }