@article{vtensorflexiblevirtualtensormanagement, title = {vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving}, author = {Jiale Xu and Rui Zhang and Cong Guo and Weiming Hu and Zihan Liu and Feiyang Wu and Yu Feng and Shixuan Sun and Changxu Shao and Yuhong Guo and Junping Zhao and Ke Zhang and Minyi Guo and Jingwen Leng}, year = {2024}, eprint = {2407.15309}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2407.15309v1}, }