@article{vsquantpervectorscaledquantizationfor, title = {VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference}, author = {Steve Dai and Rangharajan Venkatesan and Haoxing Ren and Brian Zimmer and William J. Dally and Brucek Khailany}, year = {2021}, eprint = {2102.04503}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2102.04503v1}, }