According to Gartner, 40% of generative AI solutions will be multimodal by 20271. This session offers a deep dive into running multimodal GenAI on the AI PC, a laptop built with CPU, GPU, and NPU to handle AI tasks locally and more efficiently
Specifically, it focuses on developing, optimizing, and deploying image-based models—such as Stable Diffusion and Latent Consistency Models—using multimodal learning.
Key takeaways:
- An understanding of how AI acceleration technologies are integrated across the AI PC’s hardware
- Parallels and comparisons between different GenAI algorithms and visuals; multimodal capabilities on AI PC across text, audio, and images; and lessons learned during the development and optimization processes
- Practical knowledge in implementing and deploying state-of-the-art AI models using the OpenVINO toolkit
Includes live demos showcasing the performance and power efficiency of multimodal applications on the AI PC’s GPU and NPU.
Skill level: Intermediate