@article{efficientarbitraryprecisionacceleration,
  title = {Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores},
  author = {Shaobo Ma and Chao Fang and Haikuo Shao and Zhongfeng Wang},
  year = {2024},
  eprint = {2409.17870},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.17870v2},
}