@article{progressivemixedprecisiondecodingfor,
  title = {Progressive Mixed-Precision Decoding for Efficient LLM Inference},
  author = {Hao Mark Chen and Fuwen Tan and Alexandros Kouris and Royson Lee and Hongxiang Fan and Stylianos I. Venieris},
  year = {2024},
  eprint = {2410.13461},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.13461v1},
}