@article{towardsefficientlargelanguagemodelservin,
  title = {Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization},
  author = {Jiantong Jiang and Peiyu Yang and Rui Zhang and Feng Liu},
  year = {2026},
  eprint = {2607.08057},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.08057},
}