Install OpenVINO™ Runtime via vcpkg¶
Note
Note that the vcpkg distribution:
offers C/C++ API only
does not offer support for GNA and NPU inference
is dedicated to users of all major OSes: Windows, Linux, and macOS (all x86_64 / arm64 architectures)
Installing OpenVINO Runtime¶
Make sure that you have installed vcpkg on your system. If not, follow the vcpkg installation instructions.
Install OpenVINO using the following terminal command:
vcpkg install openvino
vcpkg also enables you to install only selected components, by specifying them in the command. See the list of available features, for example:
vcpkg install 'openvino[core,cpu,ir]'
vcpkg also provides a way to install OpenVINO for any specific configuration you want via triplets, for example to install OpenVINO statically on Windows, use:
vcpkg install 'openvino:x64-windows-static'
Note that the vcpkg installation means building all packages and dependencies from source, which means the compiler stage will require additional time to complete the process.
After installation, you can use OpenVINO in your product’s cmake scripts:
find_package(OpenVINO REQUIRED)
And running from terminal:
cmake -B <build dir> -S <source dir> -DCMAKE_TOOLCHAIN_FILE=<VCPKG_ROOT>/scripts/buildsystems/vcpkg.cmake
Congratulations! You’ve just Installed and used OpenVINO in your project! For some use cases you may still need to install additional components. Check the list of additional configurations to see if your case needs any of them.
Uninstalling OpenVINO¶
To uninstall OpenVINO via vcpkg, use the following command:
vcpkg uninstall openvino
What’s Next?¶
Now that you’ve installed OpenVINO Runtime, you can try the following things:
Learn more about OpenVINO Workflow.
To prepare your models for working with OpenVINO, see Model Preparation.
See pre-trained deep learning models in our Open Model Zoo.
Learn more about Inference with OpenVINO Runtime.
See sample applications in OpenVINO toolkit Samples Overview.
Check out the OpenVINO product home page: https://software.intel.com/en-us/openvino-toolkit.