OpenVINO 2025.4 — OpenVINO™ documentation (original) (raw)
OpenVINO is an open-source toolkit for deploying performant AI solutions in the cloud, on-prem, and on the edge alike. Develop your applications with both generative and conventional AI models, coming from the most popular model frameworks. Convert, optimize, and run inference utilizing the full potential of Intel® hardware. There are three main tools in OpenVINO to meet all your deployment needs:
Where to Begin#
Installation
This guide introduces installation and learning materials for Intel® Distribution of OpenVINO™ toolkit.
Performance Benchmarks
See latest benchmark numbers for OpenVINO and OpenVINO Model Server.
Framework Compatibility
Load models directly (for TensorFlow, ONNX, PaddlePaddle) or convert to OpenVINO format.
Easy Deployment
Get started in just a few lines of code.
Model Compression
Reach for performance with post-training and training-time compression with NNCF.
Key Features#
Model Compression
You can either link directly with OpenVINO Runtime to run inference locally or use OpenVINO Model Server to serve model inference from a separate server or within Kubernetes environment.
Fast & Scalable Deployment
Write an application once, deploy it anywhere, achieving maximum performance from hardware. Automatic device discovery allows for superior deployment flexibility. OpenVINO Runtime supports Linux, Windows and MacOS and provides Python, C++ and C API. Use your preferred language and OS.
Lighter Deployment
Designed with minimal external dependencies reduces the application footprint, simplifying installation and dependency management. Popular package managers enable application dependencies to be easily installed and upgraded. Custom compilation for your specific model(s) further reduces final binary size.
Enhanced App Start-Up Time
In applications where fast start-up is required, OpenVINO significantly reduces first-inference latency by using the CPU for initial inference and then switching to another device once the model has been compiled and loaded to memory. Compiled models are cached, improving start-up time even more.