PagedMoE: Cross-Precision Expert Caching for SSD-Resident MoE Inference

Yutong Lin, Yingdi Shan, Shaoyuan Chen, Yuanyong Chen, Yongwei Wu, Mingxing Zhang · Tsinghua University · 2026
Qwen3.5-397B-A17B on a single PC, experts on NVMe SSD, DRAM cache, batch size 1
arXiv 2611.03173 Episode viz

References