-
Khadija Souissi
-
S502 - Scalable and Secure AI Inferencing with Red Hat OpenShift AI on IBM Z
Red Hat OpenShift AI provides trusted, operationally consistent capabilities for data scientists, devsecops engineers and application developers to experiment, serve models and deliver innovative applications. OpenShift AI integrates optimized vLLM framework and advanced tooling to automate deployments, self-service models, tools and resources. In this session, we will discuss how OpenShift AI integrates with IBM Z and LinuxONE to leverage IBM z17 on-chip (Telum II) and off-chip (Spyre) accelerators, auto-scaling, CI/CD for models (MLOps), and securing model endpoints for enterprise use cases. Join us to gain insights into accelerating AI adoption by operationalizing inferencing across the OpenShift ecosystem for real-time workloads in Hybrid Cloud environments.


