Lazy but Efficient: Layer-Wise Task Scheduling with Lazy Pulling for Fast Serverless Inference

Serverless inference is becoming increasingly popular in AI services thanks to its scalability and flexibility. However, high latency caused by pulling large container images and AI models remains a significant bottleneck. Lazy pulling, which pulls only the specific image layers and model layers when needed, helps reduce this latency by allowing the pulling process to overlap with inference execution in a pipeline manner. Nevertheless, we discover that lazy pulling exhibits interwoven dependencies between container image layers and AI model layers. This not only results in unnecessary idle periods where the system waits for the required layers to be pulled, but also complicates layer scheduling. To this end, in this paper, we investigate a Layer-wise Serverless Inference Scheduling (LSIS) problem, and formulate it as an Integer Linear Program (ILP) form. We further propose a LayerChain algorithm that utilizes a Variable-Length Time Slot (VL-Slot) and provides a theoretical analysis of its performance upper bound. Trace-driven evaluations demonstrate that our approach significantly reduces inference completion time compared with state-of-the-art methods by 38.49%.