@article{efimefficientservingofllmsforinfilling,
  title = {EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse},
  author = {Tianyu Guo and Hande Dong and Yichong Leng and Feng Liu and Cheater Lin and Nong Xiao and Xianwei Zhang},
  year = {2025},
  eprint = {2505.21889},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.21889v1},
}