This workshop delves into Intel® NPUs and how to deploy large language model (LLM) applications on them locally on an AI PC. Throughout the session, viewers will:

• Learn how the NPU works
• Understand its capabilities and its role in accelerating neural network computations
• Delve into the fundamental concepts underpinning NPU architecture to gain an understanding of its unique features and advantages

Through real-world examples and case studies (ChatBot*, retrieval augmented generation [RAG], Stable Diffusion*, and Text2Speech), get an overview of the seamless integration of LLM models with an Intel NPU, illustrating how this synergy can unlock unprecedented performance and efficiency.

Gain invaluable insights into the practical aspects of deploying LLM applications on an Intel NPU, from initial set up to optimization and system partitioning.