0 views

How do you deploy and run Agentic AI applications on Intel® Xeon® CPUs using Red Hat AI Quickstarts? Intel’s Alex Sin, AI Software Solutions Engineer, demonstrates.
Alex shows how to simplify AI application deployment with Helm or OpenShift commands, while using the Llama Stack API, Model Context Protocol (MCP) servers, and the VLLM model server. Alex also highlights Intel® AMX optimizations that deliver high throughput and efficient memory utilization and explores how vector databases enable Retrieval-Augmented Generation (RAG) for enterprise knowledge bases.
Date: August 6, 2026











