Red Hat OpenShift AI

Discover how to fine-tune large language models (LLMs) with Kubeflow Training, PyTorch FSDP, and Hugging Face SFTTrainer in OpenShift AI.

Explore how Red Hat Developer Hub and OpenShift AI work together with OpenShift to build workbenches and accelerate AI/ML development.

This article demystifies AI/ML models by explaining how they transform raw data into actionable business insights.

Learn how to build AI applications with OpenShift AI by integrating workbenches in Red Hat Developer Hub for training models (part 1 of 2).

Learning the naming conventions of large language models (LLMs) helps users select the right model for their needs.

This article demonstrates how to fine-tune LLMs in a distributed environment with open source tools and the Kubeflow Training Operator on Red Hat OpenShift AI.

Learn how to integrate NVIDIA NIM with OpenShift AI to build, deploy, and monitor AI-enabled applications efficiently within a unified, scalable platform.

Podman AI Lab, which integrates with Podman Desktop, provides everything you need to start developing Node.js applications that leverage large language models.

Learn how to securely integrate Microsoft Azure OpenAI Service with Red Hat OpenShift Lightspeed using temporary child credentials.

Discover how NVIDIA MIG technology on Red Hat OpenShift AI enhances GPU resource utilization.

Learn how to run distributed AI training on Red Hat OpenShift using RoCE with

Learn how to build a ModelCar container image and deploy it with OpenShift AI.

Let's take a look at how you can get started working with generative AI in your application development process using open-source tools like Podman AI Lab (https://podman-desktop.io/extensions/...) to help build and serve applications with LLMs, InstructLab (https://instructlab.ai) to fine-tune models locally from your machine, and OpenShift AI (https://developers.redhat.com/product...) to handle the operationalizing of building and serving AI on an OpenShift cluster.

Learn how to integrate Model Context Protocol (MCP) with LLMs using Node.js

This hands-on, no-nonsense guide offers practical recipes and time-saving tips that get you from first deploy to advanced CI/CD in no time.

This year's top articles on AI include an introduction to GPU programming, a guide to integrating AI code assistants, and the KServe open source project. 

Find Kubernetes and OpenShift articles on performance and scale testing, single-node OpenShift, OpenShift Virtualization for VMware vSphere admins, and more.

Join us as we get ready for the holidays with a few  AI holiday treats! We will demo AI from laptop to production using Quarkus and LangChain4j with ChatGPT, Dall-E, Podman Desktop AI and discover how we can get started with Quarkus+LangChain4j, use memory, agents and tools, play with some RAG features, and test out some images for our holiday party.

Learn how a developer can work with RAG and LLM leveraging their own data chat for queries.

Explore the evolution and future of Quarkus, Red Hat’s next-generation Java framework designed to optimize applications for cloud-native environments.

A practical example to deploy machine learning model using data science...

Repo, Red Hat Developer's new mascot, is curious, helpful, and eager to guide

Artificial intelligence (AI) and large language models (LLMs) are becoming

The rapid advancement of generative artificial intelligence (gen AI) has unlocked incredible opportunities. However, customizing and iterating on large language models (LLMs) remains a complex and resource intensive process. Training and enhancing models often involves creating multiple forks, which can lead to fragmentation and hinder collaboration.

OCI images are now available on the registries Docker Hub and Quay.io, making it even easier to use the Granite 7B large language model (LLM) and InstructLab.