Intel® Distribution of OpenVINO™ Toolkit

What's New in Version 2022.3 LTS

This release provides functional bug fixes and capability changes to the previous 2022.2 release. The new release empowers developers with new performance enhancements, more deep learning models and device portability, and higher inferencing performance with fewer code changes.  

Note This is a long-term support (LTS) release, which is issued every year and supported for two years (one year of bug fixes and two years of security patches). For details, see Intel® Distribution of OpenVINO™ Toolkit LTS Policy.

 

Release Notes

View System Requirements

Broader Model and Hardware Support

See an immediate performance boost with automatic device discovery, load balancing, and dynamic inference parallelism across CPU, GPU, and more.

  • Full support for:
    • Deep learning inferencing workloads from edge to cloud using 4th generation Intel® Xeon® Scalable processors (code name Sapphire Rapids)
    • Deep learning inferencing workloads in the intelligent cloud and the edge, and media analytics workloads using Intel’s discrete graphics cards, such as Intel® Data Center GPU Flex Series and Intel® Arc™ GPU.
  • Improved performance when using a throughput hint on a CPU plug-in for 12th and 13th generation Intel® Core™ processors (formerly code named Alder Lake and Raptor Lake).
  • Enhanced cumulative throughput and selection of compute modes added to the AUTO functionality that enables multiple accelerators (for example, multiple GPUs) to be used at once to maximize inferencing performance.

Expanded Model Coverage

Optimize and deploy with ease across an expanded range of deep learning models including natural language processing (NLP). Access AI acceleration across an expanded range of hardware.

  • Broader support for NLP models and use cases like text-to-speech and voice recognition.
  • Continued performance enhancements for computer vision models that include StyleGAN2, Stable Diffusion, RAFT for PyTorch*, and YOLOv7.
  • Significant quality and model performance improvements on Intel GPUs compared to the previous OpenVINO toolkit release.
  • New Jupyter* Notebook tutorials for Stable Diffusion text-to-image generation, YOLOv7 optimization, and 3D point cloud segmentation.

Improved API and More Integrations

It's easier to adopt and maintain code. This version requires fewer code changes, aligns better with frameworks, and minimizes conversion.

  • Preview of the TensorFlow* Front End: Load TensorFlow models directly into OpenVINO Runtime and export them to an IR format without offline conversion.
    A new –use_new_frontend flag enables this preview.
  • New Hugging Face* Optimum for Intel: Gain the performance benefits of the OpenVINO toolkit (including a neural network compression framework [NNCF]) when using Hugging Face Transformers. The initial release supports PyTorch models.
  • Intel® oneAPI Deep Neural Network Library (oneDNN) 2.7 has been updated for further refinements and significant performance improvements for the latest Intel CPU and GPU processors.
  • The C API v2.0 supports new features introduced in the OpenVINO toolkit API v2.0, such as dynamic shapes with CPU, pre- and post-processing API, unified property definition, and use. The new C API shares the same library files as the v1.0 API but with a different header file.

    Notes
    • Products based on Intel® Movidius™ VPU are not supported in this release. For support on those products, use Intel Distribution of OpenVINO toolkit 2022.1.
    • Mac* computers with the M1 processor use the Arm* device plug-in on Intel® Distribution of OpenVINO* toolkit 2022.3 LTS and later. This is a community-supported plug-in. Intel does not provide support and the plug-in does not fall under the LTS two-year support policy. For more information, see Arm* CPU Device.

Get Started

Optimize, fine-tune, and run comprehensive AI inference using the included model optimizer and runtime and development tools.

Sign Up for Exclusive News, Tips & Releases

Be among the first to learn about everything new with the Intel® Distribution of OpenVINO™ toolkit. By signing up, you get:

• Early Access product updates and releases
• Exclusive invitations to webinars and events
• Training and tutorial resources
• Contest announcements
• Other breaking news

By submitting this form, you are confirming you are an adult 18 years or older and you agree to share your personal information with Intel to use for this business request. Intel's web sites and communications are subject to our Privacy Notice and Terms of Use.
By submitting this form, you are confirming you are an adult 18 years or older and you agree to share your personal information with Intel to use for this business request. You also agree to subscribe to stay connected to the latest Intel technologies and industry trends by email and telephone. You may unsubscribe at any time. Intel's web sites and communications are subject to our Privacy Notice and Terms of Use.