@inproceedings{ye2025characterizing,
  title={Characterizing the Behavior and Impact of KV Caching on Transformer Inferences under Concurrency},
  author={Ye, Jie and Cernuda, Jaime and Maurya, Avinash and Sun, Xian-He and Kougas, Anthony and Nicolae, Bogdan},
  booktitle={IPDPS’25: The 39th IEEE International Parallel and Distributed Processing Symposium},
  year={2025}
}