@article{acceleratingllminferenceviadynamickvcach,
  title = {Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System},
  author = {Yunhua Fang and Rui Xie and Asad Ul Haq and Linsen Ma and Kaoutar El Maghraoui and Naigang Wang and Meng Wang and Liu Liu and Tong Zhang},
  year = {2025},
  eprint = {2508.13231},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.13231},
}