Skip to main content

Advancing Local AI with AMD

abstract background

Generative AI is moving beyond the cloud, enabling faster, more private AI experiences on local devices. Discover how AMD Ryzen™ AI MAX and Radeon™ R9700 technologies in the compact AMD Ryzen™ HALO form factor power high-performance AI development locally. This discussion showcases real-world GenAI workloads, highlighting AMD-powered performance, efficiency, and flexibility while exploring how local AI reduces latency, lowers cloud costs, and enables scalable next-generation AI applications.

July 22, 2026 12:20 - 13:00

Usman Pirzada
Usman Pirzada

Client AI Technologist, AMD | AMD

Topic

Agentic & Generative AI

Session Type

Meet the Experts

Related Sessions

View All Sessions
  • Advantages of Deploying Agentic AI at Work with Agent Computers

    Agentic AI is redefining the future of work by moving computing beyond user-driven interactions to intelligent agents that can reason, plan, and execute ta;Agentic AI is redefining the future of work by moving computing beyond user-driven interactions to intelligent agents that can reason, plan, and execute tasks autonomously. Discover how agent computers powered by AMD Ryzen™ AI PRO processors are unlocking a new era of enterprise productivity through faster, more responsive, and more secure local AI workflows.

    July 23, 2026

  • Build Your Openclaw Agent with Multi-Modal Models

    This is a beginner level hands-on class which will show you how to build your own Openclaw agent using opensource multi-modal models. This course will also show you how to set up an opensource model server with vLLM/SGLang and connect your agent to it.;This is a beginner level hands-on class which will show you how to build your own Openclaw agent using opensource multi-modal models. This course will also show you how to set up an opensource model server with vLLM/SGLang and connect your agent to it.

    July 23, 2026

  • Implementing Enterprise Agentic AI with AMD EPYC and AMD Instinct

    gentic AI is more than something you “chat with”. It is a digital assistant that works in cycles until the job is done. This shift from conversation to looping action is transforming business processes and fundamentally changing compute needs. In this session, learn why agentic AI is a general-purpose computing paradigm, what makes a good agent CPU, how to match infrastructure to workload needs, and how a real end customer embraced agentic AI successfully.;gentic AI is more than something you “chat with”. It is a digital assistant that works in cycles until the job is done. This shift from conversation to looping action is transforming business processes and fundamentally changing compute needs. In this session, learn why agentic AI is a general-purpose computing paradigm, what makes a good agent CPU, how to match infrastructure to workload needs, and how a real end customer embraced agentic AI successfully.

    July 23, 2026

  • Creating CPU Inference and Agentic Performance Transparency

    Move beyond generic AI: see how Open Telco Models use domain data, post-training, and AMD ROCm infrastructure to scale specialized AI.;Move beyond generic AI: see how Open Telco Models use domain data, post-training, and AMD ROCm infrastructure to scale specialized AI.

    July 23, 2026

  • Generate Video Clips in 30 Mins on AMD GPUs

    This beginner level hands-on class shows how starting from a text prompt, you can build a complete video generation pipeline and produce your first video clip within the 30 minutes. By the end, you'll have a working local setup with a Radeon GPU and a reusable ComfyUI workflow.;This beginner level hands-on class shows how starting from a text prompt, you can build a complete video generation pipeline and produce your first video clip within the 30 minutes. By the end, you'll have a working local setup with a Radeon GPU and a reusable ComfyUI workflow.

    July 22, 2026

  • Building Hybrid Multi-Agent Systems from Client to Cloud

    This is an intermediate level session to show you how to set-up Agent Computers - a hybrid multi-agent system spanning your personal AI on a Ryzen AI PC and Frontier AI models deployed on AMD Instinct GPUs for most optimum token expenditure and performance. It is recommended to join session "Build Your Openclaw Agent with Multi-Modals Models" as a prerequisite to this course.;This is an intermediate level session to show you how to set-up Agent Computers - a hybrid multi-agent system spanning your personal AI on a Ryzen AI PC and Frontier AI models deployed on AMD Instinct GPUs for most optimum token expenditure and performance. It is recommended to join session "Build Your Openclaw Agent with Multi-Modals Models" as a prerequisite to this course.

    July 22, 2026

  • Idle Capacity to Agentic AI: Scaling Inference on AMD EPYC

    Learn how AMD EPYC turns underutilized CPU infrastructure into cost-effective, high-performance AI inference for the enterprise. This session covers deployment strategies, ZenDNN acceleration, Venice quantization support, kernel optimizations, and EPYC’s role in powering Agentic AI workloads.;Learn how AMD EPYC turns underutilized CPU infrastructure into cost-effective, high-performance AI inference for the enterprise. This session covers deployment strategies, ZenDNN acceleration, Venice quantization support, kernel optimizations, and EPYC’s role in powering Agentic AI workloads.

    July 22, 2026

  • AI Infrastructure

    Your finance team doesn't care about tokens per second. They care about predictable costs, compliance risk, and vendor lock-in. With agentic AI, the metrics for tracking success are even more complex. But benchmarks don't answer the question that actually matters: Should you undertake this effort and is it viable for your business? In this interactive technical discussion, we’ll break down the tradeoffs, work through the math, and pressure-test the strategy together.;Your finance team doesn't care about tokens per second. They care about predictable costs, compliance risk, and vendor lock-in. With agentic AI, the metrics for tracking success are even more complex. But benchmarks don't answer the question that actually matters: Should you undertake this effort and is it viable for your business? In this interactive technical discussion, we’ll break down the tradeoffs, work through the math, and pressure-test the strategy together.

    July 22, 2026