@article{efficientandworkloadawarellmservingvia,
  title = {Efficient and Workload-Aware LLM Serving via Runtime Layer Swapping and KV Cache Resizing},
  author = {Zhaoyuan Su and Tingfeng Lan and ZiRui Wang and Juncheng Yang and Yue Cheng},
  year = {2025},
  eprint = {2506.02006},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.02006v1},
}