Homepage
Open in app
Sign in
Get started
OpenVINO™ toolkit
OpenVINO toolkit is a free AI toolkit facilitating the optimization of a deep learning model from a framework and deployment using an inference engine onto Intel hardware.
Model Optimize & Deploy
How-Tos
Updates
Case Studies
Deep Dives
Download
Follow
How to Run Llama 3.1 Locally with OpenVINO™
How to Run Llama 3.1 Locally with OpenVINO™
Run Llama 3.1 Locally: Optimize and Accelerate Your AI Models with OpenVINO™ and Minimal Code.
Raymond Lo, PhD
Aug 22
Build Agentic-RAG with OpenVINO™ and LlamaIndex
Build Agentic-RAG with OpenVINO™ and LlamaIndex
Enhancing LLM Capabilities with Agentic-RAG: A Comprehensive Guide to Building Advanced AI Systems Using OpenVINO™ and LlamaIndex.
Raymond Lo, PhD
Aug 16
How To Perform Real-Time People Counting on Linux AI Dev Kit With OpenVINO™
How To Perform Real-Time People Counting on Linux AI Dev Kit With OpenVINO™
Benefit from CPU, GPU, and NPU
Adrian Boguszewski
Aug 12
Introducing OpenVINO 2024.3: Enhanced LLM Performance
Introducing OpenVINO 2024.3: Enhanced LLM Performance
OpenVINO™ 2024.3 is now available! This update brings new features and enhancements especially to LLM performance.
OpenVINO™ toolkit
Aug 8
Part Two: Customizing the AI-Powered Medical Assistant with OpenVINO™
Part Two: Customizing the AI-Powered Medical Assistant with OpenVINO™
How to customize the AI medical assistant for different industries and integrate various models using OpenVINO™.
OpenVINO™ toolkit
Aug 1
Part One: Crafting an AI-Powered Medical Assistant: Transforming Healthcare with OpenVINO™
Part One: Crafting an AI-Powered Medical Assistant: Transforming Healthcare with OpenVINO™
How to build a custom AI medical assistant using OpenVINO™ toolkit.
OpenVINO™ toolkit
Aug 1
Deploy AI Faster with Intel’s OpenVINO™ Model Server
Deploy AI Faster with Intel’s OpenVINO™ Model Server
Insights into the OpenVINO Model Server, its capabilities, real-world applications, and more from Intel software engineers.
OpenVINO™ toolkit
Jul 30
Generative AI Fundamentals: Deploying LLMs with OpenVINO™
Generative AI Fundamentals: Deploying LLMs with OpenVINO™
Explore how OpenVINO simplifies LLM optimization and deployment across diverse hardware, addressing challenges in AI adoption.
OpenVINO™ toolkit
Jul 23
How to Build Faster GenAI Apps with Fewer Lines of Code using OpenVINO™ GenAI API
How to Build Faster GenAI Apps with Fewer Lines of Code using OpenVINO™ GenAI API
Authors: Raymond Lo, Dmitriy Pastushenkov, Zhuo Wu
Raymond Lo, PhD
Jul 9
How to run OpenVINO™ on a Linux AI PC
How to run OpenVINO™ on a Linux AI PC
Benefit from CPU, GPU, and NPU
Adrian Boguszewski
Jul 8
Why and How to Use OpenVINO™ Toolkit to Deploy Faster, Smaller LLMs
Why and How to Use OpenVINO™ Toolkit to Deploy Faster, Smaller LLMs
With slim deployment packages, powerful AI performance, and official Intel support, OpenVINO is ideal for running your LLM applications.
OpenVINO™ toolkit
Jul 2
Reduce LLM Footprint with OpenVINO™ Toolkit Weight Compression
Reduce LLM Footprint with OpenVINO™ Toolkit Weight Compression
Create lean LLMs using weight compression with the OpenVINO™ toolkit. Reduce LLM size, memory footprint, and GPU requirements.
OpenVINO™ toolkit
Jul 2
Accelerating SpeechBrain emotion recognition using OpenVINO™ and NNCF
Accelerating SpeechBrain emotion recognition using OpenVINO™ and NNCF
Learn about SpeechBrain, an open-source speech processing toolkit, and its optimization using Intel® OpenVINO™ and NNCF.
Pradeep Sakhamoori
Jun 25
Join Us Live or On-Demand for Exclusive AI Training
Join Us Live or On-Demand for Exclusive AI Training
We are excited to announce a new tutorial-based web series designed to provide developers with hands-on training in the world of AI.
OpenVINO™ toolkit
Jun 25
Introducing OpenVINO 2024.2:
Introducing OpenVINO 2024.2:
OpenVINO 2024.2 brings new AI capabilities: LLM-specific APIs, improved model serving, performance optimizations, new models and more!
OpenVINO™ toolkit
Jun 17
How to Serve Models on NVIDIA Triton Inference Server* with OpenVINO Backend
How to Serve Models on NVIDIA Triton Inference Server* with OpenVINO Backend
Integrate OpenVINO backend for Triton Inference Server, eliminating the need for a complete shift to OpenVINO™ Model Server.
OpenVINO™ toolkit
May 24
Mastering Multimodal AI with LLaVA-NeXT and Advanced Quantization Techniques (NNCF)
Mastering Multimodal AI with LLaVA-NeXT and Advanced Quantization Techniques (NNCF)
Explore the capabilities of multimodal AI and how OpenVINO™ optimizes these systems for real-world applications focusing on LLaVA-NeXT.
OpenVINO™ toolkit
May 22
About OpenVINO-toolkit
Latest Stories
Archive
About Medium
Terms
Privacy
Teams