Related papers: Walle: An End-to-End, General-Purpose, and Large-S…
The recent advances in virtualization technology have enabled the sharing of computing and networking resources of cloud data centers among multiple users. Virtual Network Embedding (VNE) is highly important and is an integral part of the…
We introduce Model-Distributed Inference for Large-Language Models (MDI-LLM), a novel framework designed to facilitate the deployment of state-of-the-art large-language models (LLMs) across low-power devices at the edge. This is…
YAMLE: Yet Another Machine Learning Environment is an open-source framework that facilitates rapid prototyping and experimentation with machine learning (ML) models and methods. The key motivation is to reduce repetitive work when…
The compute-storage framework is responsible for data storage and processing, and acts as the digital chassis of all upper-level businesses. The performance of the framework affects the business's processing throughput, latency, jitter, and…
The explosion of data volumes generated by an increasing number of applications is strongly impacting the evolution of distributed digital infrastructures for data analytics and machine learning (ML). While data analytics used to be mainly…
ML platforms help enable intelligent data-driven applications and maintain them with limited engineering effort. Upon sufficiently broad adoption, such platforms reach economies of scale that bring greater component reuse while improving…
Future mobile networks supporting Internet of Things are expected to provide both high throughput and low latency to user-specific services. One way to overcome this challenge is to adopt network function virtualization and Multi-access…
Deploying large language models (LLMs) on edge devices is crucial for delivering fast responses and ensuring data privacy. However, the limited storage, weight, and power of edge devices make it difficult to deploy LLM-powered applications.…
Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…
Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data. In this work, we tackle the need for problem-specific CNN…
Computational models have become one of the prevalent methods to model complex phenomena. To accurately model complex interactions, such as detailed biomolecular interactions, scientists often rely on multiscale models comprised of several…
The foundation-model ecosystem remains highly centralized because training requires immense compute resources and is therefore largely limited to large cloud operators. Edge-assisted foundation model training that harnesses spare compute on…
Recently, there has been an explosive growth of mobile and embedded applications using convolutional neural networks(CNNs). To alleviate their excessive computational demands, developers have traditionally resorted to cloud offloading,…
Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (DNNs), are too large for inference on low-power edge…
The remarkable success of the use of machine learning-based solutions for network security problems has been impeded by the developed ML models' inability to maintain efficacy when used in different network environments exhibiting different…
The recent advancements of three-dimensional (3D) data acquisition devices have spurred a new breed of applications that rely on point cloud data processing. However, processing a large volume of point cloud data brings a significant…
Solid-state storage architectures based on NAND or emerging memory devices (SSD), are fundamentally architected and optimized for both reliability and performance. Achieving these simultaneous goals requires co-design of memory components…
Edge Computing (EC) is about remodeling the way data is handled, processed, and delivered within a vast heterogeneous network. One of the fundamental concepts of EC is to push the data processing near the edge by exploiting front-end…
There is a fundamental discrepancy between the targeted and actual users of current analytics frameworks. Most systems are designed for the data and infrastructure of the Googles and Facebooks of the world---petabytes of data distributed…
A large body of research has employed Machine Learning (ML) models to develop learned operating systems (OSes) and kernels. The latter dynamically adapts to the job load and dynamically adjusts resources (CPU, IO, memory, network bandwidth)…