@misc{miao2023towards, title={Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems}, author={Xupeng Miao and Gabriele Oliaro and Zhihao Zhang and Xinhao Cheng and Hongyi Jin and Tianqi Chen and Zhihao Jia}, year={2023}, eprint={2312.15234}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2312.15234} }