Edge AI in Retail

Supplies Core Ultra client processors that combine CPU, Arc graphics and an integrated NPU, and maintains the open-source OpenVINO toolkit for optimising inference on Intel CPUs, GPUs and NPUs.

Santa Clara, California, United States

Designs the Snapdragon X platform for Windows PCs and edge clients, pairing Oryon CPU cores, Adreno graphics and the Hexagon NPU. Qualcomm also owns the Edge Impulse edge MLOps platform.

San Diego, California, United States

Publishes the Coral Edge TPU accelerators for low-power on-device inference and maintains LiteRT, the on-device runtime that succeeded TensorFlow Lite, together with the open-weight Gemma model family.

Mountain View, California, United States

Fabless SoC designer whose RK35xx application processors combine Arm CPU clusters, Mali graphics and an integrated NPU, widely used in single-board computers, panel devices and edge video products.

Fuzhou, China

Fabless company developing discrete edge AI processors, M.2 and PCIe accelerator modules and the Hailo AI Software Suite, spanning classic vision workloads and, with Hailo-10H, generative models.

Tel Aviv, Israel

Produces the IMX500 intelligent vision sensor, a stacked CMOS image sensor with an integrated AI processing block and on-chip memory, supported by the AITRIOS edge AI sensing platform.

Atsugi, Kanagawa, Japan

Builds configurable industrial computers, including fanless systems with Intel Core Ultra processors and expansion for Hailo accelerators or NVIDIA graphics cards.

South Burlington, Vermont, United States

Supplies the PowerEdge XR range of short-depth, edge-focused servers for industrial automation, video analytics and inference at retail, telecom and factory sites.

Round Rock, Texas, United States

Manufactures ThinkEdge edge servers and ThinkStation workstations, including multi-GPU platforms for local model development and EPYC-based edge systems for distributed sites.

Beijing, China / Morrisville, United States

Builds IoT SuperServer and edge box systems with Xeon Scalable processors and full-height PCIe expansion for accelerators, aimed at telecom, industrial and retail edge sites.

San Jose, California, United States

Network video manufacturer producing cameras that run deep-learning analytics on the device through AXIS Object Analytics and the open AXIS Camera Application Platform.

Lund, Sweden

Video surveillance manufacturer whose cameras include an on-board NPU for object detection, classification and licence plate recognition, with AI-assisted noise and bandwidth reduction.

Seongnam, South Korea

Provides computer vision tooling including the open-source Inference package and inference server, covering model loading, pre- and post-processing and workflow execution on edge devices.

Des Moines, Iowa, United States

Container-based platform for deploying and managing fleets of Linux edge devices, with over-the-air updates, an API and SDK, and support for a large catalogue of device types.

Remote / Seattle, United States

Originator of K3s, the lightweight CNCF-conformant Kubernetes distribution now a CNCF project, widely used to orchestrate containerised AI workloads on edge and Arm hardware.

Nuremberg, Germany

Maintainers of the ggml tensor library and llama.cpp, an MIT-licensed C and C++ inference engine that runs open-weight language models on CPUs and on CUDA, Metal and Vulkan backends.

Sofia, Bulgaria

Originated ONNX Runtime, the MIT-licensed cross-platform inference accelerator, and publishes the Phi family of small open-weight models aimed at low-latency local inference.

Redmond, Washington, United States

Publishes open-weight language and multimodal models, including Apache 2.0 licensed Mistral Small builds designed for latency-sensitive and self-hosted deployments.

Paris, France

Hosts open-weight models and publishes the SmolVLM family of compact vision-language models designed explicitly for on-device inference under the Apache 2.0 licence.

New York, United States