AI RESEARCH
Multi-DNN Inference of Sparse Models on Edge SoCs
arXiv CS.LG
•
ArXi:2603.09642v1 Announce Type: cross Modern edge applications increasingly require multi-DNN inference systems to execute tasks on heterogeneous processors, gaining performance from both concurrent execution and from matching each model to the most suited accelerator. However, existing systems only a single model (or a few sparse variants) per task, which impedes the efficiency of this matching and results in high Service Level Objective violation rates. We