@article{quickquantizationawareinterleavingand,
  title = {QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference},
  author = {Taesu Kim and Jongho Lee and Daehyun Ahn and Sarang Kim and Jiwoong Choi and Minkyu Kim and HyungJun Kim},
  year = {2024},
  eprint = {2402.10076},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.10076v1},
}