@article{areplicateandquantizestrategyforplugandp,
  title = {A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs},
  author = {Zijie Liu and Jie Peng and Jinhao Duan and Zirui Liu and Kaixiong Zhou and Mingfu Liang and Luke Simon and Xi Liu and Zhaozhuo Xu and Tianlong Chen},
  year = {2026},
  eprint = {2602.19938},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.19938},
}