@article{preserveprefetchingmodelweightsandkv,
  title = {PRESERVE: Prefetching Model Weights and KV-Cache in Distributed LLM Serving},
  author = {Ahmet Caner Yüzügüler and Jiawei Zhuang and Lukas Cavigelli},
  year = {2025},
  eprint = {2501.08192},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.08192v2},
}