@article{acceleratingllminferencethroughputvia,
  title = {Accelerating LLM Inference Throughput via Asynchronous KV Cache Prefetching},
  author = {Yanhao Dong and Yubo Miao and Weinan Li and Xiao Zheng and Chao Wang and Feng Lyu},
  year = {2025},
  eprint = {2504.06319},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.06319v1},
}