collaborators
Showing cs.DCShow all

5 papers · 1 filter

cs.DC2026

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…

cs.DC2026

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…

cs.DC2026

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…

cs.DC2026

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…

cs.DC2025

ProbSelect: Stochastic Client Selection for GPU-Accelerated Compute Devices in the 3D Continuum

Andrija Stanisic, Stefan Nastic

Integration of edge, cloud and space devices into a unified 3D continuum imposes significant challenges for client selection in federated learning systems. Traditional approaches r…