@article{baklavabudgetedallocationofkvcachefor,
  title = {BaKlaVa -- Budgeted Allocation of KV cache for Long-context Inference},
  author = {Ahmed Burak Gulhan and Krishna Teja Chitty-Venkata and Murali Emani and Mahmut Kandemir and Venkatram Vishwanath},
  year = {2025},
  eprint = {2502.13176},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.13176v1},
}