Follow
D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving https://arxiv.org/abs/2504.15299 #cs.DC #cs.AI
D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving https://arxiv.org/abs/2504.15299 #cs.DC #cs.AI