GenAI Fundamentals with OpenVINO^™

Generative AI (GenAI) models are rapidly evolving, with smaller models now proving to be as effective as their larger counterparts, offering agility and resource efficiency.

Explore the future of GenAI with our AI Evangelists and an Intel Fellow. Discover how to deploy efficient GenAI models on AI PCs and edge devices using the OpenVINO^™ toolkit for faster, smarter inference.

Key Takeaways

• Understand the balance between small and large language models (LLMs).
• Learn about LLM compression techniques like INT8, INT4, and 1-bit models.
• Discover new features in the latest OpenVINO^™ release, including broader LLM models, Mixture of Experts (MoE) architecture, and memory optimization.
• See live demos of GenAI deployment on Intel hardware.
• Gain insights into deploying AI models with OpenVINO^™ Model Server and new GenAI workloads.

Register now

Model Compression and Optimization

Learn to build computer vision and anomaly detection applications using the open-source Anomalib library for real-time defect detection, improving quality control across industries like manufacturing, healthcare, and agriculture.

Join this session to gain hands-on experience with AI inference solutions, see a robot in action, and stay updated on the latest VAND 2.0 Challenge at CVPR.

Key Takeaways

• Understand the fundamentals of the OpenVINO^™ toolkit, OpenVINO^™ runtime, and Neural Network Compression Framework (NNCF) in anomaly detection.
• Master the integration of state-of-the-art anomaly detection algorithms using Anomalib 1.0.
• Learn to train and optimize AI models for edge deployment with techniques like quantization and OpenVINO^™.
• Gain practical experience in model optimization and deployment on edge devices.
• Discuss future industry challenges in anomaly detection.

Register now

Ask it aloud. LLMs on Small Form Factor?

Explore deploying large language models (LLMs) on client PCs and small form factor at the edge, focusing on implementing a conversational voice agent.

Learn efficient techniques for deploying LLMs on resource-constrained devices using OpenVINO^™, and see how a Gradio-built interface can enhance usability.

Key Takeaways

• Understand how the Edge AI Reference Kit enables advanced LLM deployment on edge devices.
• Learn how OpenVINO^™ optimizes LLMs for AI PCs, balancing performance and power efficiency.
• Discover methods to reduce model size and computational demands for efficient LLM applications.
• Gain practical skills in implementing LLMs with OpenVINO^™ for powerful, efficient AI applications.
• See how OpenVINO^™ enhances the capabilities of LLMs on edge devices for smarter, faster AI solutions.

Register now

Bringing GenAI to AI PC

Dive into generative AI on the latest AI PCs, leveraging AI acceleration across CPU, GPU, and NPU.

Designed for developers, this session is a comprehensive overview of using GPU and NPU for image-based generative AI and using OpenVINO^™ to optimize the implementation and deployment of AI models such as Stable Diffusion, Latent Consistency Models, and more.

Key Takeaways

• Understand AI PC's AI acceleration capabilities across CPU, GPU, and NPU.
• Explore various AI use cases, including generative AI, with practical applications on AI PCs.
• Learn how generative AI applications achieve maximum performance and power efficiency using heterogeneous computing.
• Experience live demos of seamless AI application transitions across CPU, GPU, and NPU with OpenVINO^™.
• Discover how to experiment with and leverage OpenVINO^™ on AI PCs for enhancing generative AI projects.

Register now