May 20th, 2024 Presentation recorded at Santa Clara University
Large Language Models and Generative AI for High Performance Systems by Chris Cheng from HP Enterprise.
Generative AI and Large language models (LLM) with domain knowledge enhancements will fundamentally change the way we design hardware. In this talk we will start with the basic concept of transformer with encoder and decoder. We will discuss how domain knowledge can be injected into LLM through retrieval augmented generation (RAG) and fine tuning. We will also discuss the concept of LLM agent where complex design tasks can be done by the agent through planning, action with other tools and reasoning. An even more advanced technique will involve the LLM optimizing a design through optimization by prompt. We will conclude with the concept of foundational models for signal integrity and power integrity as an example of how we can tie LLM and Generative AI to complete a complex engineering design task.
2 июл 2024
