@article{moespeqspeculativequantizeddecodingwithp,
  title = {MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts},
  author = {Wenfeng Wang and Jiacheng Liu and Xiaofeng Hou and Xinfeng Xia and Peng Tang and Mingxuan Zhang and Chao Li and Minyi Guo},
  year = {2025},
  eprint = {2511.14102},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.14102},
}