Displaying 48 containers
FFNet Realtime Segmentation on Qualcomm® Hexagon™FFNet real-time semantic segmentation on Qualcomm Hexagon DSP, optimized for QCS6490 and IQ9 platforms, enabling efficient urban scene understanding with pixel-level perception for smart city street.
Intel OpenVINO™ Smart Intersection AnalyticsAccelerate smart city traffic intelligence with AI-powered multi-camera intersection analytics on Intel OpenVINO™, enabling real-time tracking, monitoring, and edge AI insights.
OpenClaw on Intel iGPU via OpenVINO™Deploy OpenClaw with local LLM acceleration on Intel iGPU via OpenVINO™ GenAI. This WSL2 Docker container enables high-performance AI agents on Advantech industrial-grade Intel Edge platforms.
.webp)
YOLO Vision Applications on AMD Ryzen™Deploy real-time Vision AI on Advantech industrial-grade AMD Ryzen™ platforms with optimized edge AI acceleration for smart inspection, analytics, and scalable AI at the edge.
.webp)
Edge RAG AI Agent on AMD Ryzen™ with ROCm™Deploy an Edge AI Agent on AMD Ryzen™ with ROCm™, delivering high-performance RAG-powered LLM workflows at the edge. Enable secure, containerized retrieval-augmented generation.
ONNX Runtime on Qualcomm HexagonSupercharge your Qualcomm QCS6490! 🚀 Run ONNX Runtime LLMs on Hexagon NPUs with one script. Our ready-to-use Python container delivers 25x faster inference. Just clone, run, and innovate!
Intel® OpenVINO™ Powered: Retail AI Self-CheckoutExperience the future of retail with Intel® OpenVINO™. Deploy this containerized AI self-checkout demo in minutes across CPU, iGPU, or NPU. Fast, repeatable, and optimized for edge performance!
Image Segmentation on Qualcomm® Hexagon™Accelerate edge AI with Qualcomm® Hexagon™-optimized image segmentation—hardware-accelerated container with dual workflows for real-time semantic vision on QCS6490 platforms.
Object Detection on Qualcomm® Hexagon™Accelerate edge AI vision with Qualcomm Hexagon-optimized YOLOv8 container — prebuilt, hardware-accelerated object detection for robotics, surveillance, and industrial vision.
LLM Ollama + OpenClaw on NVIDIA Jetson™Stop just chatting; start doing. This Jetson-optimized stack uses OpenClaw to transform Ollama into a proactive AI Agent that executes tasks and manages files across 20+ messaging channels. 🚀🤖
Mobilint NPU – LLM Inference Demo ContainerReady-to-run environment for executing various large language models (LLMs) locally on Advantech’s edge AI devices embedded with Mobilint’s ARIES-powered MLA100 MXM AI accelerator module
Literal Labs LBN: Wind Turbine Power PredictionExperience the future of energy forecasting with Literal Labs’ Logic-based Network (LBN). Deploy ultra-efficient, deterministic wind power prediction on Advantech ROM-2620 with 50x more efficiency.
1 - 12 of 48