English

Joint Partitioning and Placement of Foundation Models for Real-Time Edge AI

Distributed, Parallel, and Cluster Computing 2026-02-09 v1 Machine Learning Networking and Internet Architecture

Abstract

Inference over large-scale foundation models within heterogeneous edge environments necessitates a fundamentally reconfigurable orchestration substrate. Static partitioning of model layers presumes temporal stability across compute and network resources, which is misaligned with the volatility of real-world deployments. We introduce a framework in which both the spatial placement and internal segmentation of foundation models are elevated to runtime-resolved constructs. The orchestration problem is formalized as a constrained optimization over layer-wise assignments, subject to evolving latency, utilization, and privacy gradients. The framework implements reactive inference composition responsive to infrastructural fluctuations by integrating model-aware capacity profiling with dynamic graph re-partitioning and reallocation. We introduce architectural and algorithmic components, along with a representative use case in 6G multi-access edge computing.

Keywords

Cite

@article{arxiv.2512.01039,
  title  = {Joint Partitioning and Placement of Foundation Models for Real-Time Edge AI},
  author = {Aladin Djuhera and Fernando Koch and Alecio Binotto},
  journal= {arXiv preprint arXiv:2512.01039},
  year   = {2026}
}