@article{notokenleftbehindreliablekvcache,
  title = {No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization},
  author = {June Yong Yang and Byeongwook Kim and Jeongin Bae and Beomseok Kwon and Gunho Park and Eunho Yang and Se Jung Kwon and Dongsoo Lee},
  year = {2024},
  eprint = {2402.18096},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.18096v1},
}