Infrastructure · Infrastructure resource

Edge GPU Device

Infrastructure resourceInfrastructureInfrastructurearc:EdgeGPUDevice

An edge device with a programmable CUDA-compatible GPU for flexible accelerated inference.

Responsibility. Runs a broad range of models with GPU acceleration at the edge.

Also known as: NVIDIA Jetson AGX Orin, Edge system

Variant of GPU Node abstract

When to choose. Choose for robotics and autonomous systems needing programmable acceleration across many model types, accepting higher power draw.

hostsspecializeshostsspecializeshostshostsis target of alternativeToalternative toalternative tohostshostshostsalternative tois guarded byInference Server: hostsInference ServerGPU Node: specializesGPU NodeEdge Device Agent: hostsEdge Device AgentEdge Device: specializesEdge DeviceEdge-Optimized Model: hostsEdge-Optimized ModelGPU Telemetry Exporter: hostsGPU Telemetry ExporterEdge FPGA Device: is target of alternativeToEdge FPGA DeviceEdge NPU Device: alternative toEdge NPU DeviceEdge TPU Device: alternative toEdge TPU DeviceCluster Consensus Coordinator: hostsCluster Consensus Coordi…Edge Vision-Language Model: hostsEdge Vision-Language ModelSelf-Speculative Decoding Head: hostsSelf-Speculative Decodin…Microcontroller Device: alternative toMicrocontroller DeviceSecure Boot Verifier: is guarded bySecure Boot Verifier
Direct neighbourhood (hover for relationship types)

Relationships

hosts structural

is guarded by control

alternative to variability

Quantitative guidance

As stated by the sources; verify before use.

Classification

Technologies
NVIDIA Jetson NanoNVIDIA Jetson XavierNVIDIA Jetson OrinTensorRTCUDAcuDNNNVIDIA Jetson AGX OrinNVIDIA JetPack
Quality attributes
Flexibility (ISO/IEC 25010)Performance efficiency (ISO/IEC 25010)

Sources

  1. Ch4.3: T. Nguyen, "Container Orchestration and Edge Deployment," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.3. ISBN: 9798244538229.
  2. Ch4.6: T. Nguyen, "TensorRT-LLM and NVIDIA Fleet Command," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.6. ISBN: 9798244538229.
  3. Ch7.1A: T. Nguyen, "Advanced Implementation with Nvidia NEMO Framework and Nvlink," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.1A. ISBN: 9798244538229.
  4. Ch7.5: T. Nguyen, "NeMo Curator, Riva Speech AI & Multimodal Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.5. ISBN: 9798244538229.