相关论文: Serving DNN Models with Multi-Instance GPUs: A Cas…

Personalized recommendation is a ubiquitous application on the internet, with many industries and hyperscalers extensively leveraging Deep Learning Recommendation Models (DLRMs) for their personalization needs (like ad serving or movie…

With the rapid advancement of large language models (LLMs), efficiently serving LLM inference under limited GPU resources has become a critical challenge. Recently, an increasing number of studies have explored applying serverless computing…

To mitigate the increasingly common underutilization of computational resources in modern GPUs, spatial sharing methods enable multiple applications to use them simultaneously. This work presents a comprehensive evaluation of NVIDIA's…

Deep Neural Networks (DNNs) have significantly improved the accuracy of intelligent applications on mobile devices. DNN surgery, which partitions DNN processing between mobile devices and multi-access edge computing (MEC) servers, can…

NVIDIA's Multi-Instance GPU (MIG) technology enables partitioning GPU computing power and memory into separate hardware instances, providing complete isolation including compute resources, caches, and memory. However, prior work identifies…

The deployment of mixture-of-experts (MoE) large language models (LLMs) presents significant challenges due to their high memory demands. These challenges become even more pronounced in multi-tenant environments, where shared resources must…

Motivated by deep neural network applications, we study the problem of scheduling splittable jobs (e.g., neural network inference tasks) on configurable machines (e.g., multi-instance GPUs). We are given $n$ jobs and a set $C$ of…

Sorting is a primitive operation that is a building block for countless algorithms. As such, it is important to design sorting algorithms that approach peak performance on a range of hardware architectures. Graphics Processing Units (GPUs)…

As machine learning techniques are applied to a widening range of applications, high throughput machine learning (ML) inference servers have become critical for online service applications. Such ML inference servers pose two challenges:…

Modern machine learning workloads use large models, with complex structures, that are very expensive to execute. The devices that execute complex models are becoming increasingly heterogeneous as we see a flourishing of domain-specific…

The widespread use of Deep Neural Networks (DNNs) is limited by high computational demands, especially in constrained environments. GPUs, though effective accelerators, often face underutilization and rely on coarse-grained scheduling. This…

The deep neural network multigrid solver (DNN-MG) combines a coarse-grid finite element simulation with a deep neural network that corrects the solution on finer grid levels, thereby improving the computational efficiency. In this work, we…

In cloud environments, GPU-based deep neural network (DNN) inference servers are required to meet the Service Level Objective (SLO) latency for each workload under a specified request rate, while also minimizing GPU resource consumption.…

Modern Artificial Intelligence (AI) applications are increasingly utilizing multi-tenant deep neural networks (DNNs), which lead to a significant rise in computing complexity and the need for computing parallelism. ReRAM-based…

Graph Neural Networks (GNNs) have emerged as powerful tools for various graph mining tasks, yet existing scalable solutions often struggle to balance execution efficiency with prediction accuracy. These difficulties stem from iterative…

Ensembles of Deep Neural Networks (DNNs) have achieved qualitative predictions but they are computing and memory intensive. Therefore, the demand is growing to make them answer a heavy workload of requests with available computational…

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…

Modern computing platforms tend to deploy multiple GPUs (2, 4, or more) on a single node to boost system performance, with each GPU having a large capacity of global memory and streaming multiprocessors (SMs). GPUs are an expensive…

This work analyzes the main isolation mechanisms available in modern NVIDIA GPUs: MPS, MIG, and the recent Green Contexts, to ensure predictable inference time in safety-critical applications using deep learning models. The experimental…

With the widespread use of Internet of Things (IoT) devices and the arrival of the 5G era, edge computing has become an attractive paradigm to serve end-users and provide better QoS. Many efforts have been done to provision some merging…