DNN inferences are widely emerging as a service and must run in sub-second latency,
which need GPU hardware to achieve parallel accelerating. Prior works to improve the …

Recently, a large number of DNN inference services have emerged in public clouds, making
the low-cost deployment of DNN inference services a hot research topic. Previous studies …

GPUs are essential to accelerating the latency-sensitive deep neural network (DNN)
inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of …

The current design of Serverless computing frameworks assumes that all the requests and
underlying compute hardware are homogeneous. This homogeneity assumption causes two …

Hardware accelerators such as GPUs are required for real-time, low-latency inference with
Deep Neural Networks (DNN). However, due to the inherent limits to the parallelism they …

With the fast development of deep neural networks (DNNs), many real-world applications
are adopting multiple models to conduct compound tasks, such as co-running classification …

GPUs have been widely adopted to serve online deep learning-based services that have
stringent QoS requirements. However, emerging deep learning serving systems often result …

While deep neural network (DNN) models are often trained on GPUs, many companies and
research institutes build GPU clusters that are shared by different groups. On such GPU …

Deep neural networks (DNNs) are popular in diverse fields such as computer vision and
natural language processing. DNN inference tasks are emerging as a service provided by …

Deep Neural Networks (DNNs) are being widely applied in many advanced embedded
systems that require autonomous decision making, eg, autonomous driving and robotics. To …