@article{residualvectorquantizationforkvcache,
  title = {Residual vector quantization for KV cache compression in large language model},
  author = {Ankur Kumar},
  year = {2024},
  eprint = {2410.15704},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.15704v1},
}