Unlocking and Accelerating Generative AI with OpenVINO™ Toolkit
Generative AI has recently taken the world by storm, with models like Stable Diffusion and GPT demonstrating capabilities to create high-quality data and perform complex problem-solving. However, evaluating and adopting Foundation Models & Generative AI can quickly prove challenging due to large compute requirements and roadblocks with deployment. In this tech talk, we’ll discover how Intel® OpenVINO™ helps accelerate the end-to-end process of Generative AI building, optimization, and deployment. Key takeaways: We’ll demonstrate how to run stable diffusion and advanced transformer models on Intel® HW, including CPUs and GPUs. We will then walk-through key optimizations with OpenVINO™, including OpenVINO™ support for HuggingFace, to unlock flexible ways to develop and deploy your generative AI applications on the edge. CTA: Accelerate and deploy Generative AI on Intel® CPUs and GPUs for your use cases, leveraging Intel® hardware acceleration and OpenVINO™.
Speaker(s)
Ria Cheruvu - AI SW Architect and Evangelist/Intel
Ria Cheruvu is an AI SW Lead Architect and AI Evangelist at Intel Corporation. She has a master’s degree in data science from Harvard University, and is an instructor of data science curricula, having previously taught for Harvard University, Eduonix, Udacity, and Educative. Ria is a passionate and renowned industry speaker having delivered technical talks, podcasts, and keynotes on AI, including DEFCON, TedX, Women in Data Science communities, the QS EduData Summit, and Intel Innovation. She is a published poet, children’s book author, and neuroscience enthusiast.
