cs.AINov 10, 2026

Joint Quantization and Dynamic Partitioning for Context-Aware Edge Vision Transformers

Authors: Zhu Jiaqi, Jain Prakriti, Katare Dewant, Kumar Saurabh

Organizations: Walmart Sunnyvale, USA · Heidelberg University Heidelberg, Germany · Technische Universiteit Delft Delft, the Netherlands

Abstract

Deploying vision transformer models across connected and automated vehicles (CAVs) requires joint management of computation and Vehicle-to-Vehicle (V2V) communication. Static split-inference methods use fixed partition points and cannot adapt to time-varying link bandwidth, processing load, and concurrent multi-stream traffic. This paper proposes an edge orchestration framework that jointly selects model partition points, per-layer quantization bitwidths, and execution placement across heterogeneous vehicular compute nodes. The joint partitioning and mixed-precision allocation problem is formulated as a Mixed-Integer Linear Program (MILP) that minimizes compute and communication energy subject to end-to-end latency and task-quality constraints. The framework is evaluated on Jetson Orin Nano (8GB), Jetson Orin NX (16GB), and Jetson AGX Orin (32~GB) nodes using OPV2V-driven multi-stream workloads with K∈{2,4,6,8}K \in \{2,4,6,8\}. Across the evaluated configurations, the proposed formulation reduces V2V communication energy by 33.333.3--36.0%36.0\% relative to a Uniform INT8 split. At K=8K=8, end-to-end task completion latency is reduced by 34.0%34.0\% on the Orin Nano and 33.1%33.1\% on the Orin NX relative to the same baseline, while limiting the reduction in 3D detection accuracy to 3.13.1--4.14.1 percentage points in mAP50\mathrm{mAP}_{50} relative to FP16 execution.

Figures & tables

Explore similar work

CardsList
  1. EdgeVLN: Runtime-Aware Deployment Ready Quantized Vision Language Navigation Model

    Sep 28, 2026Rithvik Jonna, Man Namgung, Aakash Gurram +1Visual NavigationVLM Quantization

  2. MicroViTv2: Beyond the FLOPS for Edge Energy-Friendly Vision Transformers

    May 11, 2026Novendra Setyawan, Chi-Chia Sun, Mao-Hsiu Hsu +2Structural ReparameterizationEnergy-Efficient ML