11 citations · 31 across the 15 of their papers we have counts for
18 papers
Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters
Milos Gravara, Andrija Stanisic, Stefan Nastic
Compound AI workflows are increasingly used to serve complex AI tasks by coordinating multiple AI models and software components. This approach enables deployment flexibility, as e…
Constella: A Novel Framework for Cost-Efficient Distributed AI Inference in LEO Space Data Centers
Andrija Stanisic, Milos Gravara, Juan Luis Herrera +1
Space data centers built from Low-Earth Orbit (LEO) satellite constellations are gaining increasing attention as a scalable computing infrastructure. With access to abundant solar…
STORE: Self-Provisioning Storage-as-a-Service for Serverless Functions
Florian Trimmel, Cynthia Marcelino, Thomas Pusztai +1
Serverless computing provides on-demand elasticity, pay-per-use, and simplified deployment. However, serverless functions are typically stateless and depend on external storage ser…
PLAIground: SLO-Driven Runtime Model Selection for Compound AI Systems in the Edge-Cloud-Space Continuum
Milos Gravara, Cynthia Marcelino, Andrija Stanisic +1
Applications in the 3D Computing Continuum, which unifies edge, cloud, and space, require combining multiple AI tasks such as object detection, time-series analytics, and natural l…
Design Methodology and Performance Trade-offs Management for Distributed and Compound AI Systems
Milos Gravara, Andrija Stanisic, Stefan Nastic
Artificial Intelligence (AI) systems must typically satisfy service-level objectives including accuracy, latency, and cost. The prevailing model-centric approaches select a monolit…
Compass: Optimizing Compound AI Workflows for Dynamic Adaptation
Milos Gravara, Juan Luis Herrera, Stefan Nastic
Compound AI is a distributed intelligence approach that represents a unified system orchestrating specialized AI/ML models with engineered software components into AI workflows. Co…
Gaia: Hybrid Hardware Acceleration for Serverless AI in the 3D Compute Continuum
Maximilian Reisecker, Cynthia Marcelino, Thomas Pusztai +1
Serverless computing offers elastic scaling and pay-per-use execution, making it well-suited for AI workloads. As these workloads run in heterogeneous environments such as the Edge…
Roadrunner: Accelerating Data Delivery to WebAssembly-Based Serverless Functions
Cynthia Marcelino, Thomas Pusztai, Stefan Nastic
Serverless computing provides infrastructure management and elastic auto-scaling, therefore reducing operational overhead. By design serverless functions are stateless, which means…
Lumos: Performance Characterization of WebAssembly as a Serverless Runtime in the Edge-Cloud Continuum
Cynthia Marcelino, Noah Krennmair, Thomas Pusztai +1
WebAssembly has emerged as a lightweight and portable runtime to execute serverless functions, particularly in heterogeneous and resource-constrained environments such as the Edge…
Databelt: A Continuous Data Path for Serverless Workflows in the 3D Compute Continuum
Cynthia Marcelino, Leonard Guelmino, Thomas Pusztai +1
Typically, serverless functions rely on remote storage services for managing state, which can result in increased latency and network communication overhead. In a dynamic environme…
Stardust: A Scalable and Extensible Simulator for the 3D Continuum
Thomas Pusztai, Jan Hisberger, Cynthia Marcelino +1
Low Earth Orbit (LEO) satellite constellations are quickly being recognized as an upcoming extension of the Edge-Cloud Continuum into a 3D Continuum. Low-latency connectivity aroun…
CWASI: A WebAssembly Runtime Shim for Inter-function Communication in the Serverless Edge-Cloud Continuum
Cynthia Marcelino, Stefan Nastic
Serverless Computing brings advantages to the Edge-Cloud continuum, like simplified programming and infrastructure management. In composed workflows, where serverless functions nee…
Cosmos: A Cost Model for Serverless Workflows in the 3D Compute Continuum
Cynthia Marcelino, Sebastian Gollhofer-Berger, Thomas Pusztai +1
Due to the high scalability, infrastructure management, and pay-per-use pricing model, serverless computing has been adopted in a wide range of applications such as real-time data…
FedCCL: Federated Clustered Continual Learning Framework for Privacy-focused Energy Forecasting
Michael A. Helcig, Stefan Nastic
Privacy-preserving distributed model training is crucial for modern machine learning applications, yet existing Federated Learning approaches struggle with heterogeneous data distr…
GoldFish: Serverless Actors with Short-Term Memory State for the Edge-Cloud Continuum
Cynthia Marcelino, Jack Shahhoud, Stefan Nastic
Serverless Computing is a computing paradigm that provides efficient infrastructure management and elastic scalability. Serverless functions scale up or down based on demand, which…
Truffle: Efficient Data Passing for Data-Intensive Serverless Workflows in the Edge-Cloud Continuum
Cynthia Marcelino, Stefan Nastic
Serverless computing promises a scalable, reliable, and cost-effective solution for running data-intensive applications and workflows in the heterogeneous and limited-resource envi…
Towards Adaptive Asynchronous Federated Learning for Human Activity Recognition
Rastko Gajanin, Anastasiya Danilenka, Andrea Morichetta +1
In this work, we tackle the problem of performing multi-label classification in the case of extremely heterogeneous data and with decentralized Machine Learning. Solving this issue…
HyperDrive: Scheduling Serverless Functions in the Edge-Cloud-Space 3D Continuum
Thomas Pusztai, Cynthia Marcelino, Stefan Nastic
The number of Low Earth Orbit~(LEO) satellites has grown enormously in the past years. Their abundance and low orbits allow for low latency communication with a satellite almost an…