@article{pagedweightefficientmoellmservingwithdyn,
  title = {PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization},
  author = {Yuchen Yang and Yifan Zhao and Anisha Dasgupta and Sasa Misailovic},
  year = {2026},
  eprint = {2607.16184},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.16184},
}