@inproceedings{ye2026pkas,
  title={PKAS: Predictive KVCache-Aware Scheduling for Faster LLM and Transformer Inferences},
  author={Ye, Jie and Maurya, Avinash and Chitty-Venkata, Krishna Teja and Nicolae, Bogdan and Kougkas, Anthony and Sun, Xian-He},
  booktitle={Proceedings of the 2026 The 35th International Symposium on High-Performance Parallel and Distributed Computing},
  pages={402--414},
  year={2026}
}