Edge AI Deployment Beyond Models: A BSP-Aware Systems Framework for Industrial Embedded Platforms

• URL: http://arxiv.org/abs/2605.26119v1
• Date: Mon, 20 Apr 2026 17:52:05 GMT
• Title: Edge AI Deployment Beyond Models: A BSP-Aware Systems Framework for Industrial Embedded Platforms
• Abstract summary: Industrial Edge AI programs often begin with the model and only later confront the platform.<n>This paper argues that robust Edge AI deployment must be treated as a systems problem rather than a late-stage application packaging exercise.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Industrial Edge AI programs often begin with the model and only later confront the platform. That sequencing is attractive because it allows early demonstrations, but it breaks down when the deployment target is an embedded system with long product lifecycles, vendor-specific kernels, heterogeneous accelerators, safety constraints, and nontrivial I/O paths. In that environment, a model is only one component of a larger execution chain that begins at the sensor, traverses the board support package (BSP), and ends in a production service loop. This paper argues that robust Edge AI deployment must be treated as a systems problem rather than a late-stage application packaging exercise. The paper presents a BSP-aware framework for industrial embedded platforms organized around five layers: hardware, BSP/operating-system adaptation, runtime and acceleration, application/inference, and operations/validation. The discussion is grounded in vendor architecture documentation for Android, NXP i.MX, NVIDIA Jetson, ONNX Runtime, and TensorRT, and in systems literature on embedded AI benchmarking, device instability, and heterogeneous edge fleets. The result is a practical framework that connects low-level platform work to measurable deployment outcomes such as reproducibility, diagnosability, sustained throughput, and field reliability.

Related papers

• EdgeFM: Efficient Edge Inference for Vision-Language Models [11.086903401744713]
  We propose EdgeFM, a lightweight, agent-driven VLM/LLM inference framework tailored for cross-platform industrial edge deployment.<n>By allowing direct invocation of skills, it effectively closes the performance gap long dominated by proprietary toolchains.<n>We show that EdgeFM delivers favorable end-to-end inference performance, providing an open-source, production-grade solution for diverse edge industrial scenarios.
  arXiv  Detail & Related papers  (2026-04-30T06:18:50Z)
• AgenTEE: Confidential LLM Agent Execution on Edge Devices [4.9434226170553535]
  AgenTEE is a system for deploying confidential agent pipelines on edge devices.<n>It enforces strong system-level isolation of sensitive assets and runtime state.<n>Our evaluation shows that such multi-cVMs system is practical, achieving near-native performance with less than 5.15% runtime overhead.
  arXiv  Detail & Related papers  (2026-04-20T13:13:31Z)
• AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems [52.65695508605237]
  We introduce AI-NativeBench, the first application-centric and white-box AI-Native benchmark suite grounded in Model Context Protocol (MCP) and Agent-to-Agent (A2A) standards.<n>By treating agentic spans as first-class citizens within distributed traces, our methodology enables granular analysis of engineering characteristics beyond simple capabilities.<n>This work provides the first systematic evidence to guide the transition from measuring model capability to engineering reliable AI-Native systems.
  arXiv  Detail & Related papers  (2026-01-14T11:32:07Z)
• OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models [54.44308299945632]
  We introduce OS-Oracle that makes three core contributions: a scalable data pipeline for cross-platform GUI critic data; a two-stage training paradigm combining supervised fine-tuning and consistency-preserving group relative policy optimization; and OS-Critic Bench, a holistic benchmark for evaluating critic model performance across Mobile, Web, and Desktop platforms.<n>The resulting critic model, OS-Oracle-7B, achieves state-of-the-art performance among open-source VLMs on OS-Critic Bench, and surpasses proprietary models on the mobile domain.
  arXiv  Detail & Related papers  (2025-12-18T08:29:50Z)
• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs [61.953548065938385]
  We introduce the ''Three Taxes'' (Bulk Synchronous, Inter- Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework.<n>We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution.<n>We observe a 10-20% speedup in end-to-end latency over BSP-based approaches.
  arXiv  Detail & Related papers  (2025-11-04T01:15:44Z)
• On the Sustainability of AI Inferences in the Edge [3.71486243189764]
  Edge devices perform AI inferences to support latency-critical applications.<n>There is no study on their performance and energy usage for informed decision-making.<n>We analyze trade-offs among model F1 score, inference time, inference power, and memory usage.
  arXiv  Detail & Related papers  (2025-07-30T20:47:22Z)
• Secure Edge Computing Reference Architecture for Data-driven Structural Health Monitoring: Lessons Learned from Implementation and Benchmarking [0.0]
  This paper introduces a scalable and secure edge-computing reference architecture tailored for data-driven Structural Health Monitoring (SHM)<n>Our solution integrates a commercial data acquisition system with off-the-shelf hardware running an open-source edge-computing platform, remotely managed and scaled through cloud services.<n>We study this framework by collecting resource utilization data for machine learning models typically used in SHM applications on two different edge computing hardware platforms.
  arXiv  Detail & Related papers  (2025-03-24T16:33:25Z)
• Extending Lifetime of Embedded Systems by WebAssembly-based Functional Extensions Including Drivers [46.538276603099916]
  We present Wasm-IO, a framework designed to facilitate peripheral I/O operations within WebAssembly (Wasm) containers.<n>We detail synchronous I/O and methods for embedding platform-independent peripheral configurations within Wasm binaries.
  arXiv  Detail & Related papers  (2025-03-10T17:22:00Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• Auto-Split: A General Framework of Collaborative Edge-Cloud AI [49.750972428032355]
  This paper describes the techniques and engineering practice behind Auto-Split, an edge-cloud collaborative prototype of Huawei Cloud. To the best of our knowledge, there is no existing industry product that provides the capability of Deep Neural Network (DNN) splitting.
  arXiv  Detail & Related papers  (2021-08-30T08:03:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.