Related papers: iGniter: Interference-Aware GPU Resource Provision…

Deep Learning (DL), especially with Large Language Models (LLMs), brings benefits to various areas. However, DL training systems usually yield prominent idling GPU resources due to many factors, such as resource allocation and collective…

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware…

Graph Neural Networks (GNNs) have marked significant impact in traffic state prediction, social recommendation, knowledge-aware question answering and so on. As more and more users move towards cloud computing, it has become a critical…

Edge computing is being widely used for video analytics. To alleviate the inherent tension between accuracy and cost, various video analytics pipelines have been proposed to optimize the usage of GPU on edge nodes. Nonetheless, we find that…

Edge inference has become more widespread, as its diverse applications range from retail to wearable technology. Clusters of networked resource-constrained edge devices are becoming common, yet no system exists to split a DNN across these…

Many applications such as autonomous driving and augmented reality, require the concurrent running of multiple deep neural networks (DNN) that poses different levels of real-time performance requirements. However, coordinating multiple DNN…

Dynamic GNN inference has exhibited effectiveness in High Energy Physics (HEP) experiments at High Luminosity Large Hadron Collider (HL-LHC) due to strong capability to model complex particle interactions in collision events. Future HEP…

Balancing mutually diverging performance metrics, such as end-to-end latency, accuracy, and device energy consumption, is a challenging undertaking for deep neural network (DNN) inference in Just-in-Time edge environments that are…

Modern deep learning applications urge to push the model inference taking place at the edge devices for multiple reasons such as achieving shorter latency, relieving the burden of the network connecting to the cloud, and protecting user…

We propose a novel GPU-cluster scheduler for distributed DL (DDL) workloads that enables proximity based consolidation of GPU resources based on the DDL jobs' sensitivities to the anticipated communication-network delays. Our scheduler…

Graph neural networks (GNN) analysis engines are vital for real-world problems that use large graph models. Challenges for a GNN hardware platform include the ability to (a) host a variety of GNNs, (b) handle high sparsity in input vertex…

A number of production deep learning clusters have attempted to explore inference hardware for DNN training, at the off-peak serving hours with many inference GPUs idling. Conducting DNN training with a combination of heterogeneous training…

Serverless Computing (FaaS) has become a popular paradigm for deep learning inference due to the ease of deployment and pay-per-use benefits. However, current serverless inference platforms encounter the coarse-grained and static GPU…

The ability to accurately predict deep neural network (DNN) inference performance metrics, such as latency, power, and memory footprint, for an arbitrary DNN on a target hardware platform is essential to the design of DNN based models. This…

Graph Neural Networks (GNNs) play a crucial role in various fields. However, most existing deep graph learning frameworks assume pre-stored static graphs and do not support training on graph streams. In contrast, many real-world graphs are…

The surge in large language models (LLMs) has fundamentally reshaped the landscape of GPU usage patterns, creating an urgent need for more efficient management strategies. While cloud providers employ spot instances to reduce costs for…

Dynamic Graph Neural Networks (DGNNs) are becoming increasingly popular due to their effectiveness in analyzing and predicting the evolution of complex interconnected graph-based systems. However, hardware deployment of DGNNs still remains…

This paper introduces LiNR, LinkedIn's large-scale, GPU-based retrieval system. LiNR supports a billion-sized index on GPU models. We discuss our experiences and challenges in creating scalable, differentiable search indexes using…

Edge Video Analytics (EVA) has gained significant attention as a major application of pervasive computing, enabling real-time visual processing. EVA pipelines, composed of deep neural networks (DNNs), typically demand efficient inference…

The proliferation of GPU accelerated edge devices like Nvidia Jetsons and the rise in privacy concerns are placing an emphasis on concurrent DNN training and inferencing on edge devices. Inference and training have different computing and…