@article{chimeraalosslessdecodingmethodfor,
  title = {Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens},
  author = {Ziqian Zeng and Jiahong Yu and Qianshi Pang and ZiHao Wang and Huiping Zhuang and HongEn Shao and Xiaofeng Zou},
  year = {2024},
  eprint = {2402.15758},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.15758v2},
}