@article{smoothquantaccurateandefficient4bitpost, title = {SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM}, author = {Jiayi Pan and Chengcan Wang and Kaifu Zheng and Yangguang Li and Zhenyu Wang and Bin Feng}, year = {2023}, eprint = {2312.03788}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.03788v1}, }