@article{retroinferavectorstorageapproachfor, title = {RetroInfer: A Vector-Storage Approach for Scalable Long-Context LLM Inference}, author = {Yaoqi Chen and Jinkai Zhang and Baotong Lu and Qianxi Zhang and Chengruidong Zhang and Jingjia Luo and Di Liu and Huiqiang Jiang and Qi Chen and Jing Liu and Bailu Ding and Xiao Yan and Jiawei Jiang and Chen Chen and Mingxing Zhang and Yuqing Yang and Fan Yang and Mao Yang}, year = {2025}, eprint = {2505.02922}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.02922v1}, }