@misc{liu2026redknot,
  title={RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention},
  author={Yang Liu and ZhaoKai Luo and HuaYi Jin and ZhiYong Wang and RuoZhou He and BoYu Wang and Guanjie Chen and Junhao Hu},
  year={2026},
  eprint={2606.06256},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2606.06256}
}