Artificial intelligence

Learn how to set up NVIDIA NIM on Red Hat OpenShift AI and how this benefits AI and data science workloads.

Accelerate the development and deployment of enterprise AI solutions across the

Learn how the dynamic accelerator slicer operator improves GPU resource management in OpenShift by dynamically adjusting allocation based on workload needs.

Get an introduction to AI function calling using Node.js and the LangGraph.js framework, now available in the Podman AI Lab extension.

This tutorial shows you how to use the Llama Stack API to implement retrieval-augmented generation for an AI application built with Node.js.

Learn about the Red Hat OpenShift AI model fine-tuning stack and how to run performance and scale validation.

Learn how NVIDIA GPUDirect RDMA over Ethernet enhances distributed model training performance and reduces communication bottlenecks in Red Hat OpenShift AI.

Learn how the DeepSeek training process used reinforcement learning algorithms to generate human-like text and improve overall performance.

Explore performance and usability improvements in vLLM 0.8.1 on OpenShift, including crucial architectural overhauls and multimodal inference optimizations.

This Red Hat solution pattern implements key aspects of a modern IoT/edge architecture in an exemplary manner. It uses Red Hat OpenShift Container Platform and various middleware components optimized for cloud-native use. This enterprise architecture can serve as a foundation for an IoT/edge hybrid cloud environment supporting various use cases like over-the-air (OTA) deployments, driver monitoring, AI/ML, and others. Bobbycar aims to showcase an end-to-end workflow, from connecting in-vehicle components to a cloud back-end, processing telemetry data in batch or as stream, and training AI/ML models, to deploying containers through a DevSecOps pipeline and by leveraging GitOps to the edge.

Explore Knative Serving, Eventing, and Functions through an example use case. You’ll see how to collect telemetry data from simulated vehicles, process the data with OpenShift Serverless, and use the data to train a machine learning model with Red Hat OpenShift AI, Red Hat's MLOps platform. The model will then be deployed as a Knative Service, providing the inference endpoint for our business application.

A comprehensive offering for developers that includes a range of tools to

Discover a new combinatorial approach to decoding AI’s hidden logic, exploring how neural networks truly compute and reason."

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

Dive into the Q1’25 edition of Camel integration quarterly digest, covering the

The technology preview of incident detection is now available in the Red Hat OpenShift web console monitoring UI plug-in.

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).

A listing of Essential Node.js Observability Posts from Red Hat Developer and

Develop AI-integrated Java applications more efficiently using Quarkus. This article covers implementing chatbots, real-time interaction, and RAG functionality.

Discover the new Llama 4 Scout and Llama 4 Maverick models from Meta, with mixture of experts architecture, early fusion multimodality, and Day 0 model support.

Discover Async-GRPO, a new library for reinforcement learning tasks that efficiently handles large models, eliminates bottlenecks, and accelerates experiments.

Discover how the adaptive SVD approach enables LLMs to continually learn and adapt without forgetting previously acquired knowledge.

Explore how RamaLama makes it easier to share data with AI models using retrieval-augmented generation (RAG), a technique for enhancing large language models.