Speaker
Description
Abstract: In this lightning talk, we'll explore the exciting synergy between Intel's OpenVINO toolkit and Ubuntu's native support for Intel integrated and discrete GPUs. Intel's OpenVINO toolkit is an open-source framework designed to optimize and deploy deep learning models from cloud to edge. With recent Ubuntu releases, Intel GPU dependencies are now distributed directly with the operating system, marking a significant leap forward for AI developers. Key points we'll cover in 5 minutes:
Native Intel GPU Support: Ubuntu now includes essential Intel GPU packages, simplifying setup for AI development.
OpenVINO Toolkit: A brief overview of this open-source framework for optimizing and deploying AI models from cloud to edge.
Streamlined Development: How the combination of Ubuntu's Intel GPU support and OpenVINO accelerates AI application building.
Quick Demo: A rapid showcase of setting up an AI environment using Ubuntu's built-in Intel GPU support and OpenVINO.
Future Implications: The potential impact on AI development workflows and performance optimization.
This talk is perfect for developers and enthusiasts looking to leverage Ubuntu's enhanced support for Intel hardware in their AI projects. Discover how these advancements are making Ubuntu an even more powerful platform for cutting-edge AI development.
Session author's bio
As an AI Frameworks Engineer at Intel, Helena enables organizations to unlock the potential of AI by leveraging OpenVINO, Intel's AI inference runtime. She focuses on making AI accessible by enhancing developer experiences and integrating OpenVINO with popular ecosystems like Hugging Face. With a background in mathematics, Helena is passionate about empowering developers to easily deploy high-performance AI models on Intel hardware (CPUs, GPUs and NPU). Based in the Netherlands, she works to bridge the gap between complex AI technologies and practical applications.
| Level of Difficulty | Beginner |
|---|