@article{flashdecodingfasterlargelanguagemodel,
  title = {FlashDecoding++: Faster Large Language Model Inference on GPUs},
  author = {Ke Hong and Guohao Dai and Jiaming Xu and Qiuli Mao and Xiuhong Li and Jun Liu and Kangdi Chen and Yuhan Dong and Yu Wang},
  year = {2023},
  eprint = {2311.01282},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.01282v4},
}