@article{kvlinkacceleratinglargelanguagemodelsvia,
  title = {KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse},
  author = {Jingbo Yang and Bairu Hou and Wei Wei and Yujia Bao and Shiyu Chang},
  year = {2025},
  eprint = {2502.16002},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.16002v1},
}