Red Hat AI leverages enterprise AI adoption across all models, AI accelerators and clouds

New updates across Red Hat's AI portfolio drive major transformations in the enterprise industry. Through Red Hat AI, the company seeks to further extend the capabilities needed to accelerate technology adoption, offering more freedom and confidence to customers in generative AI (gen AI) deployments in hybrid cloud environments.As of the launch of Red Hat AI Inference Server, third-party validated models in Red Hat AI, and integration with the Llama Stack and Model Context Protocol (MCP) APIs, the company repositions to the market for various artificial intelligence modalities. 

According to Forrester, open source software will be the engine to accelerate enterprise AI efforts.As the AI landscape becomes more complex and dynamic, the Red Hat AI Inference Server and third-party validated models deliver efficient inference and a tested collection of performance-optimized AI models on the Red Hat AI platform. By integrating new APIs for gen AI agent development, which includes Llama Stack and MCP, Red Hat works to simplify deployment complexity, empowering IT leaders, data scientists, and developers to advance their AI initiatives with more control and efficiency.

Efficient hybrid cloud inference with Red Hat AI Inference Server

The Red Hat AI portfolio features the new Red Hat AI Inference Server, Featuring faster, more consistent and cost-effective inference at scale across hybrid cloud environments. This addition is integrated with the latest versions of Red Hat OpenShift AI and Red Hat Enterprise Linux AI, and is also available as a standalone solution, enabling organizations to deploy intelligent applications with greater efficiency, flexibility and performance.

Tried and optimized models with Red Hat AI and third-party validation

The third-party validated models of Red Hat AI, available in Hugging Face, Make it easy for businesses to choose the right models for their needs. Red Hat AI offers a collection of validated models, as well as deployment guidance that increases customer confidence in model performance and reproducibility of results. Selected models are also optimized by Red Hat, with model compression techniques that reduce their size and increase inference speed, helping to minimize resource consumption and operating costs.In addition, the continuous model validation process helps Red Hat AI customers stay at the forefront of gen AI innovation.

Standardized APIs for AI application and agent development with Llama Stack and MCP

Red Hat AI is integrating the Llama Stack'sinitially developed by Meta, together with the MCP from Anthropic, to provide standardized APIs for building and deploying AI applications and agents. Currently available in developer preview version in Red Hat AI, Llama Stack provides a unified API for inference access with vLLM, recovery-enhanced generation (RAG), model evaluation, and more guardrails and agents, in any AI gen model.MCP allows models to integrate with external tools, providing a standardized interface for connecting to APIs, plugins, and data sources in agent workflows.

The latest version of Red Hat OpenShift AI (v2.20) Provides additional improvements to build, train, deploy and monitor generative and predictive AI models at scale. Highlights include:

• Optimized model catalog (technical preview): easy access to validated Red Hat and third-party models, with web console deployment and complete lifecycle management with integrated OpenShift enrollment.

• Distributed training with KubeFlow Training Operator: run model adjustments with InstructLab and PyTorch workloads distributed across multiple Red Hat OpenShift nodes and GPUs, with distributed RDMA networking for acceleration and better GPU usage, to reduce costs. 

• Feature store (technical preview): based on the upstream Kubeflow Feast project, it offers a centralized repository for managing and delivering data for training and inference, optimizing data flow and improving model accuracy and reusability.

The Red Hat Enterprise Linux AI 1.5 brings new updates to Red Hat's core model platform, which is focused on developing, testing, and running large-scale language models (LLMs) . Key features of RHEL AI version 1.5 include:

• Availability in Google Cloud Marketplace expanding customers' choice to run Red Hat Enterprise Linux AI on public clouds (in addition to AWS and Azure), making it easier to deploy and manage AI workloads on Google Cloud.

• Enhanced capabilities in multiple languages for spanish, german, french and italian via InstructLab, allowing customization of models with native scripts and expanding the possibilities of multilingual AI applications. Users can also use their own “teacher” and “student” for greater control in customization and testing, with future support predicted for japanese, hindi and korean.

The Red Hat AI InstructLab on IBM Cloud this new cloud service further simplifies the process of customizing models, improving scalability and user experience. Enterprises can use their data more efficiently and with greater control.

Red Hat vision: any model, any accelerator, any cloud

The future of AI must be defined by unlimited opportunities and not constrained by infrastructure silos.Red Hat sees a horizon where organizations can deploy any model, on any accelerator, in any cloud, delivering an exceptional and more consistent user experience, at no exorbitant cost.To unlock the true potential of gen AI investments, companies need a universal inference platform & a new standard for continuous, high-performance AI innovations, both now and in the years to come.

Red Hat Summit

Join Red Hat Summit keynotes to hear the latest from Red Hat executives, customers, and partners:

• Modern infrastructure aligned with enterprise AI 20 May, 8h - 10h EDT (YouTube)
• Hybrid cloud evolves to drive business innovation 21 May, 8h-9h30 EDT (YouTube)