Skip to content

openvinov2026.3.0

Updated

Intel® Distribution of OpenVINO™ toolkit is an open-source toolkit for optimizing
and deploying AI inference. It can be used to develop applications and solutions based on deep learning tasks, such as: emulation of human vision, automatic speech recognition, natural language processing, recommendation systems, etc. It provides high-performance and rich deployment options, from edge to cloud

#Usage

openvino provides CMake targets:

find_package(OpenVINO REQUIRED)
target_link_libraries(main PRIVATE openvino::runtime)

#Supported Platforms

!uwp & !x86 & !(android & arm32)

  • linux
  • osx
  • windows-arm64
  • windows-x64
  • uwp
  • windows-x86

#Features

Default features: cpu, gpu, npu, auto, auto-batch, hetero, ir, onnx, paddle, pytorch, tensorflow, tensorflow-lite

#autodefault

Enables Auto plugin for inference

Dependencies:

No dependencies.

Host Dependencies:

No dependencies.

#auto-batchdefault

Enables Auto Batch plugin for inference, useful for throughput mode

Dependencies:

No dependencies.

Host Dependencies:

No dependencies.

#cpu

Enables CPU plugin for inference

Platforms: !(windows & arm)
  • linux
  • osx
  • windows-x64
  • windows-arm64
Dependencies:

No dependencies.

Host Dependencies:

No dependencies.

#gpu

Enables GPU plugin for inference

Platforms: x64 & !(osx | uwp)
  • linux
  • windows-x64
  • osx
  • windows-arm64
Dependencies:

No transitive dependencies.

Host Dependencies:
2 transitive dependencies:

#heterodefault

Enables Hetero plugin for inference

Dependencies:

No dependencies.

Host Dependencies:

No dependencies.

#irdefault

Enables IR frontend for reading models in OpenVINO IR format

Dependencies:

No dependencies.

Host Dependencies:

No dependencies.

#npu

Enables NPU plugin for inference

Platforms: x64 & !(osx | uwp)
  • linux
  • windows-x64
  • osx
  • windows-arm64
Dependencies:

No transitive dependencies.

Host Dependencies:
and 2 transitive dependencies:

#onnxdefault

Enables ONNX frontend for reading models in ONNX format

Dependencies:
and 2 transitive dependencies:
Host Dependencies:
and 2 transitive dependencies:

#paddledefault

Enables PaddlePaddle frontend for reading models in PaddlePaddle format

Dependencies:
and 2 transitive dependencies:
Host Dependencies:
and 2 transitive dependencies:

#pytorchdefault

Enables PyTorch frontend to convert models in PyTorch format

Dependencies:

No dependencies.

Host Dependencies:

No dependencies.

#tensorflowdefault

Enables TensorFlow frontend for reading models in TensorFlow format

Dependencies:
and 2 transitive dependencies:
Host Dependencies:
and 2 transitive dependencies:

#tensorflow-litedefault

Enables TensorFlow Lite frontend for reading models in TensorFlow Lite format

Dependencies:

No transitive dependencies.

Host Dependencies:
and 2 transitive dependencies:

#Dependencies

and one transitive dependency:

#Host Dependencies

No transitive dependencies.

#Used By

#Host Tool For

No ports use this.

#Contributors

  • Ilya Lavrenov's avatarIlya Lavrenov
  • Lily Wang's avatarLily Wang
  • Cheney Wang's avatarCheney Wang
  • JonLiu1993's avatarJonLiu1993
  • Billy O'Neal's avatarBilly O'Neal
  • autoantwort's avatarautoantwort
  • Tatyana Raguzova's avatarTatyana Raguzova
  • Park DongHa's avatarPark DongHa
  • Egor Tyuvaev's avatarEgor Tyuvaev
  • MonicaLiu's avatarMonicaLiu
  • Kai Pastor's avatarKai Pastor
  • Dennis's avatarDennis

#Changelog

  • aeb844b[openvino] update to 2026.3.0 (#53401)
  • 759f4cc[openvino] Avoid naming stdext::checked_array_iterator. (#51789)
  • cef6e82[openvino] update to 2026.1.0 (#51141)
  • ff9d90fopenvino: fix debug build by making pdbs in windows (#50299)
  • 9ce9d26[openvino] update to 2026.0.0 (#50155)
  • 1f6bbba[protobuf] update to 6.33.4 (#49107)
  • 4acadb7[openvino] update to 2025.3.0 (#47185)
  • a5ea3ca[openvino] update to 2025.2.0 (#46147)
  • 32ed571[openvino] Update to 2025.1 (#44954)
  • d447aba[vcpkg baseline][openvino] version 2025.0.0 (#43659)
Show 30 earlier changes