Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

NEW RELEASE: OpenVINO 2024.1 is here!

Luis_at_Intel
Moderator
1,459 Views

We're excited to announce the latest release of the OpenVINO toolkit, 2024.1. This update brings enhancements in LLM performance, empowering your generative AI workloads with OpenVINO.

What’s new in this release:

 

More Gen AI coverage and framework integrations to minimize code changes.

  • Support for the newly released state-of-the-art Llama 3 model.
  • Mixtral and URLNet models optimized for performance improvements on Intel® Xeon® Processors.
  • Stable Diffusion 1.5, ChatGLM3-6b, and Qwen-7B models optimized for improved inference speed on Intel® Core™ Ultra processors with integrated GPU.
  • Now available support for Falcon-7b-Instruct, a GenAI LLM ready-to-use chat/instruct model with superior performance metrics.
  • New Jupyter Notebooks added: Yolo V9, Yolo V8 Oriented Bounding Boxes Detection (OOB), Stable Diffusion in Keras, MobileCLIP, RMBG-v1.4 Background Removal, Magika, TripoSR, AnimateAnyone, LLaVA-Next and RAG system with OpenVINO and LangChain 

Broader LLM model support and more model compression techniques.

  • LLM compilation time reduced through additional optimizations with compressed embedding. Improved 1st token performance of LLMs on 4th and 5th generations of Intel® Xeon® Platforms with Intel® Advanced Matrix Extensions (Intel® AMX).
  • Better LLM compression and improved performance with oneDNN,  INT4 and INT8 support for Intel® Arc™ GPUs.
  • Significant memory reduction for select smaller GenAI models on Intel® Core™ Ultra processors with integrated GPU.

More portability and performance to run AI at the edge, in the cloud, or locally.

  • The preview NPU plugin  for Intel® Core™ Ultra processors is now available in the OpenVINO open-source GitHub repository, in addition to the main OpenVINO package on PyPI.
  • The JavaScript API is now more easily accessible through the npm repository, enabling JavaScript developers' seamless access to the OpenVINO API. 
  • FP16 inference on ARM processors now enabled for the Convolutional Neural Network (CNN) by default.

 

Download the 2024.1 Release 
Download Latest Release Now

 

Get all the details 
See 2024.1 release notes 

 

NNCF RELEASE

Check out the new NNCF release

 

Helpful Links

NOTE: Links open in a new window.

0 Replies
Reply