EDGE-AI-INFERENCE

AI model inference on specialised edge devices.

Definition

Edge AI Inference hardware: NVIDIA Jetson Nano/Xavier/Orin (1-275 TOPS), Google Coral Edge TPU (4 TOPS), Intel Neural Compute Stick 2, Qualcomm Cloud AI 100, Hailo-8 (26 TOPS), Apple Neural Engine. Frameworks: TensorFlow Lite, PyTorch Mobile, ONNX Runtime, NVIDIA TensorRT, OpenVINO Intel. Use cases: Industrial computer vision (defect detection, predictive maintenance), Retail (customer counting, planogram compliance), Healthcare (local diagnostic imaging), Automotive (ADAS, autonomous driving).

Origin

Edge AI emergence ~2017 with NVIDIA Jetson TX1 and Google Coral ; massification 2020+ with IoT and 5G growth ; market ~$5 billion 2024.

Example in context

Foxconn deploys 2000 NVIDIA Jetson Xavier on its iPhone assembly lines ; each inspects 500 boards/hour with YOLOv8 model detecting micro-defects in sub-50ms.

Related terms

• Edge computing B2B — parent paradigm.