Dělen: Enabling Flexible and Adaptive Model-serving for Multi-tenant Edge AI

Model-serving systems expose machine learning (ML) models to applications programmatically via a high-level API. Cloud platforms use these systems to mask the complexities of optimally managing resources and servicing inference requests across multiple applications. Model serving at the edge is now also becoming increasingly important to support inference workloads with tight latency requirements. However, edge model serving differs substantially from cloud model serving in its latency, energy, and accuracy constraints: these systems must support multiple applications with widely different latency and accuracy requirements on embedded edge accelerators with limited computational and energy resources. To address the problem, this paper presents Dělen,1 a flexible and adaptive model-serving system for multi-tenant edge AI. Dělen exposes a high-level API that enables individual edge applications to specify a bound at runtime on the latency, accuracy, or energy of their inference requests. We efficiently implement Dělen using conditional execution in multi-exit deep neural networks (DNNs), which enables granular control over inference requests, and evaluate it on a resource-constrained Jetson Nano edge accelerator. We evaluate Dělen flexibility by implementing state-of-the-art adaptation policies using Dělen’s API, and evaluate its adaptability under different workload dynamics and goals when running single and multiple applications.