@article{costefficientllmservinginthecloudvm,
  title = {Cost-Efficient LLM Serving in the Cloud: VM Selection with KV Cache Offloading},
  author = {Kihyun Kim and Jinwoo Kim and Hyunsun Chung and Myung-Hoon Cha and Hong-Yeon Kim and Youngjae Kim},
  year = {2025},
  eprint = {2504.11816},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.11816v1},
}