HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference

Publication
In Design Automation Conference (DAC)
Shuzhang Zhong
PhD Student (2023)
Meng Li
Meng Li
Assistant Professor

I develop efficient and privacy-preserving AI systems through algorithm–hardware co-design, with applications in large language models, embodied AI, and multimodal intelligence.