Red Hat announced that it has completed its acquisition of Neural Magic, a pioneer in software and algorithms that accelerate generative AI (gen AI) inference workloads. With Neural Magic, Red Hat adds expertise in inference performance engineering and model optimization, helping further the company's vision of high-performing AI workloads that directly map to unique customer use cases, wherever needed across the hybrid cloud.

The large language models (LLMs) underpinning today's gen AI use cases, while innovative, are often too expensive and resource-intensive for most organizations to use effectively. To address these challenges, Red Hat views smaller, optimized and open source-licensed models driven by open innovation across compute architectures and deployment environments as key to the future success of AI strategies.

Neural Magic's commitment to making optimized and efficient AI models a reality furthers Red Hat's ability to deliver on this vision for AI. Neural Magic is also a leading contributor to vLLM, an open source project developed by UC Berkeley for open model serving, which will help bring even greater choice and accessibility in how organizations build and deploy AI workloads.

The future of hybrid cloud-ready gen AI

With Neural Magic's technology and performance engineering expertise, Red Hat aims to break through the challenges of wide-scale enterprise AI, using open source innovation to further democratize access to AI's transformative power via:

• Open source-licensed models, from the 1B to 100's of billions parameter scale, that can run anywhere and everywhere needed across the hybrid cloud - in corporate data centers, on multiple clouds and at the edge.
• Fine-tuning capabilities that enable organizations to more easily customize LLMs to their private data and uses cases with a stronger security footprint;
• Inference performance engineering expertise, resulting in greater operational and infrastructure efficiencies; and
• A partner and open source ecosystem and support structures that enable broader customer choice, from LLMs and tooling to certified server hardware and underlying chip architectures.

The concept of choice is as crucial for gen AI today as it was cloud-native or containerized applications several years ago: The right environment (cloud, server, edge, etc.), accelerated compute and inference server are all critical for successful gen AI strategies. Red Hat remains firm in its commitment to customer choice across the hybrid cloud, including AI, with the acquisition of Neural Magic furthering supporting this promise.

Red Hat AI: An open source backbone for AI

The expertise and capabilities of Neural Magic will be incorporated into Red Hat AI, Red Hat's portfolio of gen AI platforms. Built with the hybrid cloud in mind, Red Hat AI encompasses:

• Red Hat Enterprise Linux AI (RHEL AI), a foundation model platform to more seamlessly develop, test and run the IBM Granite family of open source-licensed LLMs for enterprise applications on Linux server deployments;
• Red Hat OpenShift AI, an AI platform that provides tools to rapidly develop, train, serve and monitor machine learning models across distributed Kubernetes environments on-site, in the public cloud or at the edge; and
• InstructLab, an approachable open source AI community project created by Red Hat and IBM that enables anyone to shape the future of gen AI via the collaborative improvement of open source-licensed Granite LLMs using InstructLab's fine-tuning technology.

vLLM, LLM Compressor, pre-optimized models and more are all slated to be incorporated into Red Hat AI, making Neural Magic an integral piece of Red Hat's AI platform offerings.