@article{behnam2025empiric,
  title = {{EMPIRIC}: Exploring Missing Pieces in {KV} Cache Compression for Reducing Computation, Storage, and Latency in Long-Context {LLM} Inference},
  author = {Payman Behnam and Yaosheng Fu and Ritchie Zhao and Po-An Tsai and Zhiding Yu and Alexey Tumanov},
  year = {2025},
  month = {August},
  journal = {ACM SIGOPS Operating Systems Review},
  volume = {59},
  number = {1},
  pages = {46--54},
  doi = {10.1145/3759441.3759448},
}
