Serving DNN Inference With Fine-Grained Spatio-Temporal Sharing of GPU Servers

Abstract

Deep Neural Networks (DNNs) are commonly deployed as online inference services. To meet interactive latency requirements of requests, DNN services require the use of Graphics Processing Unit (GPU) to improve their responsiveness. The unique characteristics of inference workloads pose new challenges to manage GPU resources. First, the GPU scheduler needs to carefully manage requests to meet their latency targets. Second, a single inference task often underutilizes GPU resources. Third, the fluctuating patterns of inference workloads pose difficulties in determining the resources allocated to each DNN model. Therefore, it is critical for the GPU scheduler to maximize GPU utilization by collocating multiple DNN models without violating the latency Service-Level Objectives (SLOs) of requests. However, we find that existing works are not adequate for achieving this goal among latency-sensitive inference tasks. Hence, we propose FineST, a scheduling framework for serving DNNs with fine-grained spatio-temporal sharing of GPU inference servers. To maximize GPU utilization, FineST allocates intra-GPU computing resources from both spatial and temporal dimensions across DNNs in a cost-effective way, while predicting interference overheads under diverse consolidated executions for controlling SLO violation rates. Compared to a state-of-the-art work, FineST improves the peak throughput of serving heterogeneous DNNsby up to 64.7% under SLO constraints.