Chapter 1. About Red Hat AI Inference Server supported hardware and software
Red Hat AI software runs on a variety of supported hardware, software, and delivery platforms in production environments.
Technology Preview and Developer Preview features are provided for early access to potential new features.
Technology Preview or Developer Preview features are not supported or recommended for production workloads.
Supported configurations span multiple AI accelerator types including NVIDIA GPUs, AMD GPUs, Google TPUs, and IBM Spyre accelerators. Red Hat AI Inference Server can be deployed in OpenShift Container Platform clusters, on standalone Red Hat Enterprise Linux (RHEL) hosts with Podman, or integrated with Red Hat OpenShift AI for managed AI/ML workflows.