@article{pqcacheproductquantizationbasedkvcache,
  title = {PQCache: Product Quantization-based KVCache for Long Context LLM Inference},
  author = {Hailin Zhang and Xiaodong Ji and Yilin Chen and Fangcheng Fu and Xupeng Miao and Xiaonan Nie and WeiPeng Chen and Bin Cui},
  year = {2024},
  eprint = {2407.12820},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.12820v2},
}