@article{firpfasterllminferenceviafuture,
  title = {FIRP: Faster LLM inference via future intermediate representation prediction},
  author = {Pengfei Wu and Jiahao Liu and Zhuocheng Gong and Qifan Wang and Jinpeng Li and Jingang Wang and Xunliang Cai and Dongyan Zhao},
  year = {2024},
  eprint = {2410.20488},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.20488v1},
}