Red Hat AI

Accelerate the development and deployment of enterprise AI solutions across the hybrid cloud.

Try Red Hat AI Inference Explore the developer program
Red Hat AI cube
  1. Home
  2. Products
  3. Overview

Deliver AI solutions with Red Hat AI

Red Hat® AI provides the control to simplify and accelerate agentic AI adoption. Connect models to data, integrate with agents, and scale across the hybrid cloud with your choice of models and accelerators.

Red Hat AI logo overlaid on top of cube tower

Get a sneak peak of the new O’Reilly tech guide: AI Inference at Scale 
 

Preview a sample of the upcoming O’Reilly technical guide: AI Inference at Scale. Take a closer look at AI inference and aligning the input of work with the output of results. 

The full guide will be available in February 2027.  

See the preview

What's included in Red Hat AI?

The Red Hat AI portfolio streamlines the development, deployment, lifecycle management, and governance of predictive, generative, and agentic AI. Powered by open source technologies, it provides operational control across any combination of hardware, cloud providers, and datacenters. 

Red Hat AI Enterprise

Red Hat AI Enterprise is an integrated AI platform for building and running efficient, cost-effective AI models, agentic AI workflows, and AI-powered applications on any infrastructure. 

  • Build, fine-tune, and manage workflows for generative, predictive, and agentic AI applications.
  • High throughput, low-latency model serving with intelligent scaling.


Learn more

Try It

Red Hat Inference

Deploy your preferred models faster and more cost-effectively across the hybrid cloud with Red Hat AI Inference.

Features and benefits include:

  • vLLM runtime maximizes inference throughput and minimizes latency
  • Pre-optimized model repository for rapid model serving
  • LLM compressor reduces compute costs without sacrificing accuracy


Learn more

Try It

Red Hat OpenShift AI

Red Hat OpenShift AI is an MLOps platform that lets you quickly build, train, and deploy AI models and applications across hybrid cloud environments.

Features and benefits include:

  • Enterprise MLOps capabilities
  • Hardware accelerators and hybrid cloud support for building and delivering AI at scale


Learn more

Try It

Red Hat Enterprise Linux AI

Red Hat Enterprise Linux AI is a foundation model platform that helps simplify and accelerate generative AI model development, testing, and deployment within enterprise environments.

Features and benefits include:

  • IBM’s Granite family large language models (LLMs)
  • Cost-efficient GPU access

 

Learn more

Try It

Red Hat AI: Powered by open source

Red Hat’s product development is rooted in open source and community innovation. Explore the upstream communities that build Red Hat AI.

vllm-logo

vLLM

vLLM, which stands for virtual large language model, is a library of open source code that helps LLMs perform calculations more efficiently and at scale. Specifically, vLLM is an inference server that speeds up the output of gen AI applications by making better use of GPU memory.

Read about vLLM inference
Llm-d Llm-d kubernetes

Llm-d

llm-d is a Kubernetes-native open source framework for distributed large language model (LLM) inference. It supports the complex requirements for LLM inference at scale by prioritizing efficiency.

 

Read about Llm-d
granite logo

Granite

Granite is IBM’s third generation of AI language models. Fit for purpose and open source, these enterprise-ready, multimodal models deliver exceptional performance against safety benchmarks and across a wide range of enterprise tasks, from cybersecurity to retrieval-augmented generation (RAG).

Read about Granite models
Open Data Hub and Kubeflow installation customization

Open Data Hub

Red Hat OpenShift AI is based on the upstream project Open Data Hub, which is a blueprint for building an AI-as-a-Service platform on Red Hat's Kubernetes-based OpenShift Container Platform. Open Data Hub is a meta-project that integrates over 20 open source AI/ML projects into a practical solution.

Learn more about Open Data Hub
Jupyter logomark

Jupyter

Project Jupyter, which spun off from the IPython Project in 2014, supports interactive data science and scientific computing across all programming languages. Jupyter is supported by a community of data enthusiasts who believe in the power of open tools and standards for education, research, and data analytics.

Create a notebook with JupyterLab
Tensorflow logomark

TensorFlow

TensorFlow is an end-to-end, open source platform for machine learning (ML). Its comprehensive, flexible ecosystem of tools, libraries, and community resources helps developers easily build and deploy ML-powered applications.

Build and evaluate a model with TensorFlow and ONNX
Pytorch logomark

PyTorch

PyTorch is an open source machine learning framework that fast-tracks the path from research prototyping to production deployment. It is used for applications such as computer vision and natural language processing.

Optimize PyTorch training
Mlflow logo

MLflow

MLflow is an open-source platform, purpose-built to assist machine learning practitioners and teams in handling the complexities of the machine learning process. MLflow focuses on the full lifecycle for machine learning projects, ensuring that each phase is manageable, traceable, and reproducible.

Learn how MLflow works
Kubeflow

Kubeflow

Kubeflow is an open source framework aimed at simplifying AI/ML workflow deployment at scale. Red Hat OpenShift AI integrates the Kubeflow notebook controller, model serving, and data science pipeline components into the core product.

Fine-tune LLMs with Kubeflow

Featured Red Hat AI blogs & articles

Article Observability Hero

Learn how to integrate OpenTelemetry with a zero trust workload identity...

Article Featured image for vLLM interference article.

Learn how speculative decoding in vLLM can significantly increase throughput...

Article A stylized illustration representing an artificial neural network, set against a dark purple background within a slightly rounded, darker purple square icon shape. The neural network consists of multiple layers of interconnected nodes, depicted as glossy, spherical red orbs. Lines connect these red orbs, forming a complex web. White arrow shapes extend horizontally from the left side, pointing towards the network, suggesting input or data flowing into the system.

Learn how to combine KServe and llm-d to optimize generative AI inference,...

Article Red Hat AI

Learn how to build security hygiene into OpenClaw by using containers for...

Article Featured image for AI/ML

Learn how to use Claude AI as a pattern matcher to refactor legacy test...

Article Featured image for agentic AI

Explore how Red Hat AI simplifies agent deployment with OpenClaw, showcasing...

Ready to use Red Hat AI in production?

Take your deployment to the next level. Transitioning to production with Red Hat AI offers you enhanced stability, security, and support. Our dedicated team is here to ensure a smooth migration and to help with any questions you may have.

Talk to an expert
ai-ready-to-use-collage