Red Hat AI 3

What's New

This content is not included.

Red Hat OpenShift AI 3 Release Notes

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

This content is not included.

Red Hat AI Inference 3 Release Notes

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

This content is not included.

Red Hat Enterprise Linux AI 3 Release Notes

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

Discover

This content is not included.

Discover Red Hat OpenShift AI 3

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

Discover Red Hat OpenShift AI 2

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

This content is not included.

Discover Red Hat AI Inference 3

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

This content is not included.

Discover Red Hat Enterprise Linux AI 3

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

This content is not included.

Discover Red Hat AI Enterprise

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

Get started

Introduction to Red Hat AI

Red Hat AI is a portfolio of products and services that accelerates the development and deployment of AI solutions across hybrid cloud environments

This content is not included.

Get started with projects, workbenches, and pipelines in OpenShift AI

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

Plan

Prepare your platform and hardware for Red Hat AI

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

Choose a validated model for reliable serving

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

Install

This content is not included.

Deploy and decommission OpenShift AI on your cluster

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

This content is not included.

Deploy and decommission OpenShift AI in disconnected environments

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

Assess and plan for migration from OpenShift AI 2.25.4 to 3.3.2

Assess and plan for migration to Red Hat OpenShift AI Self-Managed 3.3.2

This content is not included.

Install Red Hat Enterprise Linux AI on bare metal and cloud

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

This content is not included.

Deploy the AI Inference container with GPU/TPU acceleration

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

Administer

This content is not included.

Operate a governed, multi‑tenant AI platform at scale

Use CRDs or dashboard to publish images and provision resourced workbenches

This content is not included.

Administer OpenShift AI platform access, apps, and operations

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

This content is not included.

Manage and serve ML features with Feature Store

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

This content is not included.

Understand, control, and audit usage telemetry in OpenShift AI

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

This content is not included.

Provision hardware configurations and resources for projects

Enable supported hardware configurations for your data science workloads

This content is not included.

Configure single‑ and multi‑model serving for your cluster

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

This content is not included.

Build AI/Agentic Applications with Llama Stack

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

This content is not included.

Configure user access, storage, and telemetry in OpenShift AI

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

This content is not included.

Enable the model registry to track, version, and deploy models

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

This content is not included.

Provision and secure access to model registries

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

Choose production‑ready OpenShift AI APIs

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

Develop

This content is not included.

Register, version, and promote models with the model registry

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

This content is not included.

Discover, evaluate, register, and deploy models from the model catalog

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

Deploy the RAG stack for projects

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

This content is not included.

Experiment with RAG in the AI playground

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

This content is not included.

Accelerate data processing and training with distributed workloads

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

This content is not included.

Connect your workbench to S3-compatible object storage

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

This content is not included.

Organize projects, collaborate in workbenches, and deploy models

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

This content is not included.

Use the Red Hat data science IDE images effectively

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

This content is not included.

Build, schedule, and track machine learning pipelines

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

This content is not included.

Enable and manage connected applications from the OpenShift AI dashboard

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

Train

This content is not included.

Customize Models for Gen AI and Agentic AI Applications

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

Evaluate

This content is not included.

Evaluating AI systems

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

Maintain Safety

This content is not included.

Ensuring AI safety with guardrails

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

Monitor

This content is not included.

Monitoring your AI Systems

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

Deploy

This content is not included.

Deploy large models using the single-model serving platform (KServe RawDeployment)

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

This content is not included.

Deploy models using Distributed Inference with llm-d

Deploy and serve large language models at scale in Red Hat OpenShift AI

This content is not included.

Govern LLM access with Models-as-a-Service

Govern LLM access with Models-as-a-service in Red Hat OpenShift AI Self-Managed

Inference

This content is not included.

Get started with Red Hat Enterprise Linux AI for inference

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

This content is not included.

Deploy the AI Inference container with AI acceleration

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

This content is not included.

Deploy the AI Inference on OpenShift with supported accelerators

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

This content is not included.

Deploy the AI Inference in disconnected environments

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

This content is not included.

Package, deploy, and serve OCI model containers on OpenShfit

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

This content is not included.

Tune vLLM server settings to optimize model serving

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

This content is not included.

Compress and optimize LLMs with the Red Hat AI Model Optimization Toolkit

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

Learn

This content is not included.

Red Hat AI Foundations

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

This content is not included.

Red Hat AI learning hub

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