@article{dualgrainedquantizationefficientfine, title = {Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM}, author = {Luoming Zhang and Wen Fei and Weijia Wu and Yefei He and Zhenyu Lou and Hong Zhou}, year = {2023}, eprint = {2310.04836}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.04836v1}, }