Supercharge Inferencing of GenAI & LLM on AI PC

In this session, we will introduce how to run local, fast AI inferencing for LLM and gen AI on AI PC with the help of OpenVINO, of which the main points are:

a) AI PC quick overview

b) OpenVINO Notebooks intro & demo (quick demos/GIFs of different use cases on CPU, GPU and NPU)

c) Challenges of AI deployment and general overview of OpenVINO (developer journey)

d) Introduction of main features intro, including - Model converter - NNCF (weights compression for LLM) - Optimum-Intel (GenAI) - Deployment (AUTO plugin)