Red Hat and Rebellions have announced the integration of Red Hat OpenShift AI with Rebellions’ neural processing units (NPUs), creating a full-stack enterprise AI platform aimed at increasing flexibility and choice for businesses. The collaboration combines Red Hat’s open source AI inference capabilities with Rebellions’ energy-efficient NPUs, addressing key issues faced by organizations deploying artificial intelligence at scale.
As companies increasingly implement AI in business operations, they encounter challenges such as high infrastructure costs, deployment complexity, and the need for flexible yet secure environments. Traditional GPU-based systems may not always provide the necessary performance or efficiency for these workloads. The new offering seeks to enable more efficient operation of AI tasks across various environments.
Rebellions’ NPUs are built specifically for AI inference, providing greater energy efficiency than standard GPUs and helping reduce data center operational expenses. Their software stack supports major open source AI frameworks, aiming to offer developers a familiar experience similar to that of working with GPUs.
The integrated solution has been validated by both Red Hat and Rebellions for enterprise use. The Rebellions NPU Operator is certified for Red Hat OpenShift, allowing smoother integration across on-premises and multi-cloud setups while supporting compliance with data sovereignty regulations.
Brian Stevens, senior vice president and chief technology officer for AI at Red Hat, stated: “The future of enterprise AI demands architectural choice beyond proprietary, monolithic stacks. Our collaboration with Rebellions is a powerful step in delivering Red Hat’s ‘any model, any accelerator, any cloud’ strategy. By tightly integrating the open, scalable capabilities of Red Hat OpenShift AI with Rebellions’ energy-efficient NPUs, we’re giving enterprises a validated, full-stack alternative. This enables customers to deploy their most demanding AI inference workloads with the required efficiency, low latency, and horizontal scalability that is critical for production AI.”
Sung Hyun Park, CEO of Rebellions added: “As AI serving and inference accelerate, enterprises need practical infrastructure that meets their requirements for performance, cost efficiency, and data sovereignty. Through this collaboration, Red Hat and Rebellions will provide a validated, end-to-end inference platform that replaces the fragmented approaches of the past. This will help enterprises scale their AI services more efficiently and securely, while also presenting a new NPU-based alternative to the traditionally GPU-centric environment.”
Red Hat OpenShift AI powered by Rebellions NPUs aims to address common obstacles in adopting generative AI technologies—including managing costs related to infrastructure and operations as well as meeting regulatory requirements regarding data management—by offering an enterprise-ready solution capable of running large language models with high throughput and low latency.
