BYOD Lab: Leverage Generative AI on z/OS using zCX, IBM Spyre and Red Hat AI Inference Server
Project and Program:
New and Innovative Technologies,
Machine Learning / AI
Tags:
Proceedings,
2026,
SHARE Pittsburgh 2026
In this Lab we will learn how to leverage a simple AI chatbot running in a container on zCX to demonstrate generative AI inferencing requests using Red Hat Inferencing Server and IBM Spyre accelerators on z/OS using zCX. We will leverage Granite 3.3 8B Instruct model using the vLLM runtime on IBM Spyre accelerators, and validate the deployment through prompt-driven user interactions using simple AI Chatbot.
Back to Proceedings File Library