Introduction

Overview of AI Services

AI Services are part of the IBM Open-Source AI Foundation for Power and are designed for Power11 systems, which provides adoption patterns, pre-built AI Services ("AI Services") and packages for integrating with inferencing solutions such as Red Hat AI Inference Server. AI Services integrate with and are optimized for the IBM Spyre™ Accelerator for Power infrastructure.

Designed for simplicity and speed, AI Services enable rapid deployment and easy installation — helping enterprises accelerate digital transformations, streamline processes, and boost productivity. Each AI Service is a self-contained deployment unit, powered by advanced inferencing capabilities. AI Services support a wide range of AI models, including large language models (LLMs), embedding models, and re-ranker models. With IBM Spyre™ for Power's AI Services running on IBM Power and flexible consumption options for LLM inferencing, businesses can scale AI seamlessly and efficiently.

Source code at