FusedInf: Efficient Swapping of DNN Models for On-Demand Serverless Inference Services on the Edge

TL;DR

This paper introduces FusedInf to efficiently swap DNN models for on-demand serverless inference services on the edge by combining multiple models into a single Direct Acyclic Graph (DAG) to efficiently load the models into the GPU memory and make execution faster.

Abstract

Edge AI computing boxes are a new class of computing devices that are aimed to revolutionize the AI industry. These compact and robust hardware units bring the power of AI processing directly to the source of data--on the edge of the network. On the other hand, on-demand serverless inference services are becoming more and more popular as they minimize the infrastructural cost associated with hosting and running DNN models for small to medium-sized businesses. However, these computing devices are still constrained in terms of resource availability. As such, the service providers need to load and unload models efficiently in order to meet the growing demand. In this paper, we introduce FusedInf to efficiently swap DNN models for on-demand serverless inference services on the edge. FusedInf combines multiple models into a single Direct Acyclic Graph (DAG) to efficiently load the models into the GPU memory and make execution faster. Our evaluation of popular DNN models showed that creating a single DAG can make the execution of the models up to 14\% faster while reducing the memory requirement by up to 17\%. The prototype implementation is available at https://github.com/SifatTaj/FusedInf.

Figures (9)

• Figure 1: Effectiveness of FusedInf when concurrently executing multiple DNN models for inference on the edge.
• Figure 2: DNN model execution timeline on a GPU.
• Figure 3: Efficiency in function invocation when compiling a single DAG of multiple models.
• Figure 4: FusedInf system architecture.
• Figure 5: Graph compilation process of FusedInf with multiple DNN models.