@article{improvingtheservingperformanceofmulti,
  title = {Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management},
  author = {Hang Zhang and Jiuchen Shi and Yixiao Wang and Quan Chen and Yizhou Shan and Minyi Guo},
  year = {2025},
  eprint = {2505.03756},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.03756v1},
}