@article{smoothquantaccurateandefficientpost, title = {SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models}, author = {Guangxuan Xiao and Ji Lin and Mickael Seznec and Hao Wu and Julien Demouth and Song Han}, year = {2022}, eprint = {2211.10438}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2211.10438v7}, }