DIAMoND: Dynamic Inference for Adaptive Edge MOE with Heterogeneous In-NAND and Near-DRAM Compute Architecture.
Ling Liang, Tianyang Luo, Shuzhang Zhong, Dongxue Zhao, Qichao Ma, Renjie Wei, Jingyu Wang, Meng Li, Guangyu Sun, Zongwei Wang, Yimao Cai
Browse the full ISCA paper archive.