面向边缘视觉 Transformer 的联合量化与动态分区方法
Joint Quantization and Dynamic Partitioning for Context-Aware Edge Vision Transformers
AI 导读
一篇 arXiv 论文提出面向车联网的边缘编排框架，联合选择模型分区点、逐层量化位宽和异构车载计算节点上的执行位置，并将该问题建模为 MILP。
正文 · 原文
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 (8~GB), Jetson Orin NX (16~GB), and Jetson AGX Orin (32~GB) nodes using OPV2V-driven multi-stream workloads with $K \in \{2,4,6,8\}$. Across the evaluated configurations, the proposed formulation reduces V2V communication energy by $33.3$--$36.0\%$ relative to a Uniform INT8 split. At $K=8$, end-to-end task completion latency is reduced by $34.0\%$ on the Orin Nano and $33.1\%$ on the Orin NX relative to the same baseline, while limiting the reduction in 3D detection accuracy to $3.1$--$4.1$ percentage points in $\mathrm{mAP}_{50}$ relative to FP16 execution.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.14196 [cs.AI] |
| (or arXiv:2611.14196v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14196 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Saurabh Kumar [view email]
[v1]
Tue, 10 Nov 2026 15:18:00 UTC (1,333 KB)
来源：arXiv cs.AI · arxiv.org