Kubernetes

Follow this 4-step process using Training Hub and OpenShift AI to transition LLM fine-tuning from local experiments to repeatable, production-grade workflows.

Learn how Dynamic Resource Allocation (DRA) in OpenShift 4.21 fundamentally changes how GPU and accelerator resources are requested, allocated, and shared across your cluster. This post covers what DRA is, why it matters, what's new in OpenShift 4.21, and how to use it with real examples running on an OpenShift 4.21 cluster with NVIDIA A100 GPUs.

Learn how to deploy multiple large language models (LLMs) behind a single OpenAI-compatible endpoint on OpenShift using a Model-as-a-Service (MaaS) approach. This guide demonstrates how to build an intelligent routing infrastructure that dynamically inspects the request payload and directs traffic based on the specified model field, reducing GPU waste and simplifying application logic.

Learn how to install and configure the cluster observability operator to monitor the health of your OpenShift and Kubernetes components.

Learn how to integrate Red Hat Advanced Cluster Management with Argo CD for efficient application control. Discover how to use both push and pull models, and configure Argo CD to watch Policy resources.

Learn how to upgrade Red Hat Advanced Cluster Management hubs with zero downtime.

How to rebalance control plane workloads on Red Hat Advanced Cluster Management hub clusters and solve scaling bottlenecks with managed cluster migration.

Discover a solution for simplifying and automating the management of multi-network policies (MNP) at scale using Red Hat Advanced Cluster Management.

Announcing the Red Hat Advanced Cluster Management 2.16 general availability (GA) of namespace and virtualization right-sizing recommendations.

Learn how to streamline Red Hat OpenShift AI dependency management using Kustomize and GitOps. Use the odh-gitops repo to automate setup via CLI or Argo CD.

Learn how to run high-performance computing workloads managed by Slurm within a containerized OpenShift environment using the Slinky operator.

Explore the latest features in Network Observability 1.11, an operator for Red Hat OpenShift and Kubernetes that provides insights into your network traffic flows.

Learn how to deploy and test an Earth and space model inference service on Red Hat AI Inference Server and Red Hat OpenShift AI. This article includes two self-contained activities, one deploying Prithvi using a traditional Deployment object and another serving the model using KServe and observing Knative scaling.

This guide shows how to stop managing storage users by hand and start using a GitOps approach to do it automatically.

Learn how hosted control planes reduce costs without compromising performance by using intelligent scaling.

Learn about the Red Hat build of OpenTelemetry and its auto-instrumentation capabilities to achieve full-stack observability on OpenShift.

Learn how to implement TokenRateLimitPolicy for LLM APIs. This approach to advanced rate limiting ensures fair use and better cost management in AI workflows.

Learn how to build a zero trust environment using Red Hat Connectivity Link and manage connectivity between services, gateways, and identity providers.

Discover the new features in Red Hat Advanced Cluster Security that allow integrating component health and security data into Prometheus for better observability and alerting.

Headed to DevNexus? Visit the Red Hat Developer booth on-site to speak to our expert technologists.

Learn how to upgrade volume performance on OpenShift without downtime using VolumeAttributesClass. Follow this hands-on demo to get started.

Red Hat OpenShift 4.21 introduces AI-driven insights, automated security signing, and local development tools to help you build and deploy faster.

Install the Kiali Model Context Protocol server into OpenShift Lightspeed to transform Kiali into an active data source and streamline AI-driven operations.

Go beyond ports 80 and 443. Learn how to configure Kubernetes LoadBalancer services to expose UDP, database, and VM traffic outside your cluster.

This guide details how to use curl and jq to retrieve and format CVE data in readable text and structured CSV formats for data analysis and security tasks.