Red Hat AI
Accelerate the development and deployment of enterprise AI solutions across the hybrid cloud.
Deliver AI solutions with Red Hat AI
Red Hat AI provides the flexibility and consistency you need to deploy and manage predictive and generative AI models for your organization’s workload strategy. The Red Hat AI portfolio includes Red Hat Enterprise Linux AI for individual Linux server environments and Red Hat OpenShift AI for distributed Kubernetes platform environments.
Red Hat AI provides access to small, fit-for-purpose models based on the open source Granite model family that are efficient, cost-effective, and fully supported by Red Hat. It also enables simple yet powerful model tuning with InstructLab, making it easy to align and customize models with your organization’s private data.
Introducing Red Hat AI Inference Server
Deploy your preferred models faster and more cost-effectively across the hybrid cloud with Red Hat AI Inference Server. Its vLLM runtime maximizes inference throughput and minimizes latency. A pre-optimized model repository ensures rapid model serving, while the LLM compressor reduces compute costs without sacrificing accuracy. Experience fast, accurate inference for a wide range of applications.
Red Hat AI Inference Server is included in Red Hat OpenShift AI and Red Hat Enterprise Linux AI and supported on Red Hat OpenShift and Red Hat Enterprise Linux.
Red Hat AI use cases
Discover what’s possible with Red Hat AI.
Build, migrate, and run machine learning and predictive AI models
Build machine learning models on your own and leverage advanced AI tooling for delivering predictive models. Red Hat AI also provides support for ITOps teams that want to manage and run models from a Kubernetes-based platform.
Build, deliver, and run generative AI applications
Get access to Granite models, InstructLab, and development tools for delivering generative AI applications.
Safeguard your data with private AI
Red Hat AI provides support for both predictive and generative AI model development and delivery, whether in on-premise data centers or in your own private cloud. Red Hat AI helps reduce the risk of exposing sensitive data by providing support for on-premise and air-gapped deployments.
Operationalize your AI models
Accelerate your move from experimentation to production with the tools you need to automate the model life cycle. Red Hat AI streamlines model training, validation, storing, and serving by combining MLOps and DevOps capabilities in a single platform.
Multi-architecture AI deployments
Red Hat AI provides support for multi-cloud, hybrid cloud, and hardware acceleration architectures to ensure high-performance stability and scalability across various infrastructures.
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.
Featured Red Hat AI blogs & articles
Introducing InstructLab, an open source project for enhancing large language...
Learn how to build a ModelCar container image and deploy it with OpenShift AI.
Learn how to install the Red Hat OpenShift AI operator and its components in...
Learn how to integrate NVIDIA NIM with OpenShift AI to build, deploy, and...
Discover the new Llama 4 Scout and Llama 4 Maverick models from Meta, with...
Explore inference performance improvements that help vLLM serve DeepSeek AI...
Explore how vLLM's new multimodal AI inference capabilities enhance...
Learn how to fine-tune large language models with specific skills and...
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.
