Product Documentation for Red Hat AI 3

Highlights of what is new and what has changed with the latest OpenShift AI 3 release

Highlights of what is new and what has changed with the latest Red Hat AI Inference Server 3 release

Highlights of what is new and what has changed with the latest Red Hat Enterprise Linux AI 3 release

Use CRDs or dashboard to publish images and provision resourced workbenches

Administer access, apps, resources, and accelerators; maintain logging, audit, and backups

Use Feature Store to define, store, and serve reusable machine learning features to models

Help administrators decide what usage data is collected, see what’s included, and enable or disable telemetry

Enable supported hardware configurations for your data science workloads

Enable single‑model, multi‑model, or NVIDIA NIM serving platforms with serving runtimes and deployment modes

Operate Llama Stack: activate the operator and expose OpenAI‑compatible RAG APIs

As an administrator, configure user access, customize the dashboard, and manage specialized resources for data science and AI engineering projects

Enable the model registry so teams can register models and versions, capture metadata and provenance, and promote approved versions to serving with consistent governance

Use the OpenShift AI dashboard to create registries, set access with RBAC groups, and manage model and version lifecycle so teams can register, share, and promote models to serving with traceability

Plan which APIs to build on and how to upgrade with minimal risk by mapping each OpenShift AI endpoint to a support tier that defines stability and deprecation timelines

Review compatibility matrices, accelerator support, deployment targets, and update policy prior to installation

Explore the curated set of third‑party models validated for Red Hat AI products, ready for fast, reliable deployment

OpenShift AI 3 is a hybrid platform to build, serve, and monitor models at scale

OpenShift AI 2 is a hybrid platform to build, serve, and monitor models at scale

Serve LLMs with low latency on your preferred hardware, using vLLM optimizations

Serve and optimize your AI models on a Linux appliance, with low‑latency vLLM performance

Red Hat AI Enterprise is an integrated enterprise environment for deploying, managing, and scaling AI model inference, training and tuning, and agentic AI workloads

Store, version, and promote models with metadata for cross‑project sharing and traceability

Use the model catalog to discover, evaluate, register, and deploy models for rapid customization and testing

Enable LlamaStack, GPUs, and vLLM, ingest data in a vector store and expose secure endpoints

Using the AI playground to experiment with RAG using models from your catalog

Distribute data and ML jobs for faster results, larger datasets, and GPU‑aware auto‑scaling and monitoring

Create a connection, configure an S3 client, and list, read, write, and copy objects from notebooks

Organize projects, collaborate in workbenches, build notebooks, train/deploy models, and automate pipelines

Launch a workbench, pick an IDE, and develop with prebuilt images or custom environments

Define KFP‑based pipelines, version and schedule runs, and track artifacts in S3‑compatible storage

Enable applications, connect with keys, remove unused tiles, and access Jupyter from the dashboard

Get set up to create projects, launch workbenches, and deploy your first model on OpenShift AI

Install via Operator or CLI, enable required components, verify the deployment, and cleanly uninstall when needed

Install via Operator or CLI, enable required components, verify the deployment, and cleanly uninstall when needed

As the OpenShift AI 3.0 release introduces significant changes, and is a fast release, we want to ensure a smooth migration path from 2.x stable (eg 2.25) to the first stable 3.x release. As a result, upgrade from 2.x to 3.0 is not available

Deploy Red Hat Enterprise Linux AI using the bootable container image on servers or cloud

Choose the container image for your accelerator, run the server, and confirm access to your GPUs/TPUs with a sample request

Customize AI models that are specific to your domain-specific use case, from setting up your development environment to building and deploying models for use in generative AI applications

Configure LMEvalJobs, select tasks, run evaluations, and retrieve metrics to compare model performance

Orchestrate detectors to filter LLM inputs/outputs, auto‑configure security, and expose guarded endpoints

Monitor model bias and data drift by configuring metrics, thresholds, and visualizations in OpenShift AI

Deploy models with KServe—choose RawDeployment or Knative, set resources and runtimes, and expose authenticated endpoints

Get started with Red Hat Enterprise Linux AI 3, a generative AI inference platform for Linux environments that uses Red Hat AI Inference Server for running and optimizing models

Choose the container image for your accelerator, run the server, and confirm access to your AI acclerators with a sample request

Install GPU operators, configure secrets and storage, deploy models, and expose secure inference endpoints

Mirror required images, configure registry and secrets, and deploy secure inference endpoints offline

Package models as OCI images, push to a registry, deploy, and serve on GPUs

Choose and set key vLLM flags—parallelism, memory, batching, networking—to deploy reliable, performant endpoints

Use LLM Compressor to apply quantization or sparsity and prepare compressed models for deployment

Follow one of the no-cost learning paths tailored to business leaders and technology learners in order to boost AI skills and confidence while earning Credly certificates

Explore a curated collection of learning resources designed to help you accomplish key tasks with Red Hat AI products and services