Testing modern hash table designs in OVN and OVS | Red Hat Developer

Experiments in optimizing OVN and OVS hashmap performance with Swiss tables

developers.redhat.com

Trace Kubernetes resources for llm-d model serving | Red Hat Developer

Explore Kubernetes resources for Red Hat AI Inference on Amazon EKS, enabling intelligent routing for your model serving

developers.redhat.com

OpenCost 1.121.0: First-of-a-kind Kubernetes inference cost tracking

Your GPU bill is rising. Your models are serving billions of tokens. Yet one question remains unanswered: what does each token actually cost? This is not a hypothetical problem.

cncf.io

AutoRAG: Optimizing RAG for small models | Red Hat Developer

Stop guessing RAG settings. Discover how AutoRAG uses fast evaluation sweeps to optimize chunking and retrieval precision for small LLMs on your data

developers.redhat.com

One kernel feature, 93% system throughput gone: A Red Hat Enterprise Linux 10.2 kernel regression and how to mitigate it | Red Hat Developer

A kernel scheduler regression in RHEL 10.2 caused up to 93% throughput loss on CockroachDB across multiple AWS instance types. The regression is bimodal, causing workloads to either run at full speed

developers.redhat.com

You can’t debug what you can’t see — Observability for AI Agents

Traditional APM can’t tell you why your agent spent far more than usual asking the same question three times. We’ve been running AI agents in production for months. The hardest part isn’t building…

cncf.io

Multitenant AI inference with dynamic resource allocation on OpenShift | Red Hat Developer

Learn how to run isolated Llama 3.1 8B workloads on a single NVIDIA H100 GPU using OpenShift, Kubernetes dynamic resource allocation, and NVIDIA MIG

developers.redhat.com

Stop patching and build a better WordPress stack with Red Hat Hardened Images | Red Hat Developer

Deploy WordPress on Red Hat Hardened Images and image mode for RHEL—less time firefighting vulnerabilities, more time shipping features

developers.redhat.com

Kubeflow SDK evolution- One million downloads and counting

The unified kubeflow-sdk has officially crossed 1 million downloads on PyPI! This milestone reflects the rapid adoption of this streamlined interface. In this post, we celebrate this community…

cncf.io

Cortex completes OSTIF security audit

The Open Source Technology Improvement Fund is proud to share the results of our security audit of Cortex. Cortex functions as a long-term, multi-tenant scalable open source storage for Prometheus and...

cncf.io

Inference-time scaling on Red Hat AI: Improving model reliability | Red Hat Developer

Improve model reliability at inference time with its_hub: Learn how to select accurate outputs without retraining

developers.redhat.com

Scaling Kubernetes pods with KEDA based on Amazon SQS queue depth

In event-driven Kubernetes architectures, CPU and memory utilization often fail to reflect real system pressure. A worker pod may sit idle from a CPU perspective while thousands of messages pile up in...

cncf.io

Behavioral testing for AI agents | Red Hat Developer

Learn behavioral testing for agents, catching non-deterministic failures with golden queries and YAML files

developers.redhat.com

Optimize GPU efficiency with OpenShift AI and llm-d flow-control | Red Hat Developer

Optimize GPU efficiency with Red Hat OpenShift AI 3.4's flow control for llm-d, ensuring priority-based request queuing and fairness policies

developers.redhat.com

Runtime Supply Chain Verification using the Node Resource Interface (NRI)

The widely used container supply chain verification tools today operate at the Kubernetes API layer as admission webhooks (such as Kyverno, OPA Gatekeeper, and Sigstore Policy Controller).

cncf.io

Quarkus 3.38 - Weight-based eviction for Hibernate second level Caffeine cache, and more

Quarkus: Supersonic Subatomic Java

quarkus.io

To Cache or Not to Cache Virtual Threads

Quarkus: Supersonic Subatomic Java

quarkus.io

Enrich OpenShift compliance results with custom metadata | Red Hat Developer

Improve OpenShift compliance with custom metadata: Attach business-specific labels and annotations to Rule objects for better automation and auditability

developers.redhat.com

OSFT explained: Prevent catastrophic forgetting in LLM fine-tuning | Red Hat Developer

Learn how to preserve existing model knowledge with Orthogonal Subspace Fine-Tuning (OSFT) for fine-tuning large language models in Training Hub

developers.redhat.com

Build a distributed RAG pipeline with Ray Data on OpenShift AI | Red Hat Developer

Learn how to build a distributed RAG pipeline with Ray Data on OpenShift AI for high-performance parsing, embedding, and writing to a vector database

developers.redhat.com

MCP 7-28 Release Party — Celebrate With AAIF - Agentic AI Foundation (AAIF)

Join MCP 7-28 release parties across 6 cities on July 28-29. Meet AI practitioners, MCP maintainers, and community builders. RSVP now.

aaif.io

How to use LVM with shared storage | Red Hat Developer

Learn how to dynamically split shared storage space with LVM on SAN

developers.redhat.com

Standardize project context with AGENTS.md and Agent Skills | Red Hat Developer

Boost AI coding agent performance with AGENTS.md and Agent Skills. Learn how to standardize project context, structure tasks, and share skills across teams

developers.redhat.com

How we designed customizable dashboards in OpenShift | Red Hat Developer

Learn how to build custom Red Hat OpenShift monitoring dashboards with PromQL, drag-and-drop layouts, and full GitOps support for your workflows

developers.redhat.com

Federating clusters for zero-downtime Kubernetes

Every multi-region setup eventually meets the same awkward moment: a whole cluster goes away, and the identical copy of your service running two regions over might as well not exist…

cncf.io