@article{nuqmmquantizedmatmulforefficient,
  title = {LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models},
  author = {Gunho Park and Baeseong Park and Minsub Kim and Sungjae Lee and Jeonghoon Kim and Beomseok Kwon and Se Jung Kwon and Byeongwook Kim and Youngjoo Lee and Dongsoo Lee},
  year = {2022},
  eprint = {2206.09557},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2206.09557v4},
}