PKAS: Predictive KVCache-Aware Scheduling for Faster LLM and Transformer Inferences

Copy BibTeX

@inproceedings{ye2026pkas,
  grc_key = {ye2026pkas},
  grc_slug = {ye-2026-pkas-predictive-kvcache-aware-scheduling-for-81cf},
  author = {Ye, J. and Maurya, A. and Chitty-Venkata, K. and Nicolae, B. and Kougkas, A. and Sun, X.-H.},
  title = {{PKAS: Predictive KVCache-Aware Scheduling for Faster LLM and Transformer Inferences}},
  booktitle = {35th International Symposium on High-Performance Parallel and Distributed Computing (HPDC 2026)},
  year = {2026},
  month = jul,
  publisher = {ACM},
  pages = {402--414},
  publication_status = {published},
  doi = {10.1145/3806645.3807819},
  url = {https://doi.org/10.1145/3806645.3807819},
  source_url = {http://cs.iit.edu/%7Escs/assets/files/ye2026pkas.pdf},
  keywords = {KV Cache Management, LLM Inference Serving, Scheduling},
}