@article{asurveyonefficientinferenceforlarge, title = {A Survey on Efficient Inference for Large Language Models}, author = {Zixuan Zhou and Xuefei Ning and Ke Hong and Tianyu Fu and Jiaming Xu and Shiyao Li and Yuming Lou and Luning Wang and Zhihang Yuan and Xiuhong Li and Shengen Yan and Guohao Dai and Xiao-Ping Zhang and Yuhan Dong and Yu Wang}, year = {2024}, eprint = {2404.14294}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.14294v3}, }