@article{sdqsparsedecomposedquantizationforllm,
  title = {SDQ: Sparse Decomposed Quantization for LLM Inference},
  author = {Geonhwa Jeong and Po-An Tsai and Stephen W. Keckler and Tushar Krishna},
  year = {2024},
  eprint = {2406.13868},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.13868v1},
}