HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference.
Shuzhang Zhong, Yanfan Sun, Ling Liang, Runsheng Wang, Ru Huang, Meng Li
Browse the full DAC paper archive.
Shuzhang Zhong, Yanfan Sun, Ling Liang, Runsheng Wang, Ru Huang, Meng Li
Browse the full DAC paper archive.