Red Hat OpenShift AI
Red Hat's larger AI platform, and the second option IBM accepts for driving a Spyre Accelerator on IBM Power.
Red Hat OpenShift AI includes the same vLLM-based serving capability found in Red Hat AI Inference Server, wrapped in a full container platform with model lifecycle management, pipelines, and separation between teams and projects. It runs on Red Hat OpenShift, so adopting it brings container orchestration and its skills requirement along with it. It is the sensible option when several models, several teams, or several servers are involved. Choosing it purely to satisfy a Spyre prerequisite that the lighter product also satisfies is a common and costly mistake.
Related Terms
Red Hat AI Inference Server
Red Hat's model serving product, built on the open source vLLM engine. IBM lists it as one of two supported ways to drive a Spyre Accelerator on IBM Power.
Spyre Accelerator
IBM's PCIe AI inference card. On IBM Power 11 it carries 32 cores, 128 GB of memory, and more than 300 TOPS inside a 75 watt envelope.
vLLM
The open source model serving engine inside Red Hat AI Inference Server, known for PagedAttention and continuous batching.