@article{peekpredictivequeueinformedkvcachemanage, title = {PEEK: Predictive Queue-Informed KV Cache Management for LLM Serving}, author = {Bing Xie and Zhipeng Wang and Masahiro Tanaka and Zheng Zhen}, year = {2026}, eprint = {2607.02525}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.02525}, }