KV Cache Compression for Inference Efficiency in LLMs: A Review

@misc{zhang2025kvcachecompression,
      title={KV Cache Compression for Inference Efficiency in LLMs: A Review},
      author={Shouhua Zhang and Jiehan Zhou and Yanyu Liu and Yitian Zou and Jingying Fu and Sixiang Liu and You Fu},
      year={2025},
      eprint={2508.06297},
      archivePrefix={arXiv},
      primaryClass={cs.DC},
      url={https://arxiv.org/abs/2508.06297},
}