DALI: A Workload-Aware Offloading Framework for Efficient MoE Inference on Local PCs
Overview
Workload-aware offloading for efficient mixture-of-experts inference on local PCs.
通过工作负载感知卸载,优化本地 PC 上的混合专家模型(MoE)推理。
Preprint, 2026. See the linked paper for the full method, experiments, and latest version.
Research by Minnan Pei (裴旻楠) and collaborators · Email