Location: Room P9 – Peony Jr 4411 (Level 4)
Abstract: Explore the future of AI with AMD’s expert-led, hands-on workshops.
Join Getting Started with AMD Ryzen AI PC to build and customize your own AI agent or attend AI Science Discovery Made Easier with ROCm and AMD Instinct Accelerators to deploy and optimize Large Language Models (LLMs) with vLLM and SGLang. Gain practical insights, live demos, and valuable expertise from industry specialists.
Choose to attend one or both workshops and enhance your AI knowledge.
RSVP now and attend the workshop to stand a chance to win a Poly Sync 20 Wireless Speakerphone or a Lenovo ThinkVision M14 Monitor!
Plus, the first 20 attendees per session receive an additional gift.
RSVP Today: https://forms.gle/V81xQhWXkVwuzVAx7
Programme:
| Time | Session |
| 10:00am – 12:00pm | Getting Started with AMD Ryzen AI PC With the help of AI PCs, people can enjoy better gaming experiences and smoother workflows. This sharing will help you explore the potential of Ryzen AI PCs and briefly describe their powerful applications, such as live demonstrations of object detection, LLM and diffusion-based deployment on Edge, ensuring participants gain practical insights into AI implementation. The presenters will guide participants through a hands-on experience, designed to kick-start their journey towards mastering AI using state of art AMD AI PC technology. Attendees will have the unique opportunity to construct and customize their own AI Agent, helping everyone start their AI journey with AI PCs. – Ms Sonya Yang, Software Development Engineer, AMD Research and Advanced Development (RAD), AMD University Program (AUP), Advanced Micro Devices, Inc (AMD) |
| 02:00pm – 06:00pm | AI science discovery made easier with ROCm and AMD Instinct Accelerators The application of open-source software development ecosystems, coupled with the most capable GPU Accelerators, is a driving force behind the AI Mega trend fueling business, scientific research and exploration of new frontiers today. We will introduce AMD ROCm and explore how to easily deploy Large Language Models (LLMs) with vLLM and SGLang, using popular examples now applied to scientific research domains. For example, Llama V3.x and Deepseek. In addition, we will look at tuning approaches to best optimize model training and inference. Note: This will be an instructor lead workshop with demos, but no individual access to MI300X GPUs. However, as there will be references to online resources and model repositories, you are encouraged to bring along a laptop to follow along and explore the live material. Documentation including the presentation and demos shown will be provided as handouts at the workshop. A basic knowledge of Pytorch, Docker Containers, AI training and AI Inference is expected for maximum benefit and understanding. AMD is planning a follow-up workshop in Singapore, featuring hands-on lab exercises with AMD MI300X GPUs after SCAsia 2025. The exact date is yet to be confirmed. Visit the AMD booth #C4 at SCA to register your interest. – Mr Greg Oakes, Senior HPC and Artificial Intelligence Specialist, AMD Global HPC and AI Centre of Excellence, Advanced Micro Devices, Inc (AMD) |
