# openshift\_ai

Published articles for openshift\_ai.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Deploy R models on Red Hat OpenShift AI with KServe

DevFeed: [Deploy R models on Red Hat OpenShift AI with KServe](<https://devfeed.tech/articles/deploy-r-models-on-red-hat-openshift-ai-with-kserve-144330.md>)

Original publisher: [Read original article](<https://developers.redhat.com/articles/2026/11/19/deploy-r-models-red-hat-openshift-ai-kserve>)

Author: Anneli Sara Banderby

Published: 2026-11-19T14:16:36Z

Content type: tutorial

Language: en

Sources: [Red Hat](<https://devfeed.tech/sources/red-hat.md>), [Red Hat Developer](<https://devfeed.tech/sources/red-hat-developer.md>)

Topics: [KServe](<https://devfeed.tech/topics/kserve.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [redhat ubi](<https://devfeed.tech/topics/redhat-ubi.md>), [redhat](<https://devfeed.tech/topics/redhat.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [api](<https://devfeed.tech/tags/api.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [autoscaling](<https://devfeed.tech/tags/autoscaling.md>), [cli](<https://devfeed.tech/tags/cli.md>), [containers](<https://devfeed.tech/tags/containers.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [kserve](<https://devfeed.tech/tags/kserve.md>), [models](<https://devfeed.tech/tags/models.md>), [openshift](<https://devfeed.tech/tags/openshift.md>), [openshift-ai](<https://devfeed.tech/tags/openshift-ai.md>), [r](<https://devfeed.tech/tags/r.md>), [red-hat-openshift](<https://devfeed.tech/tags/red-hat-openshift.md>)

### AI overview

The guide shows how to serve R models on Red Hat OpenShift AI by building a custom KServe runtime, packaging a model in an OCI ModelCar, registering the runtime, and deploying through either CLI manifests or the web console. The runtime supports .rds models with a predict() method, plus .qs2, .rda, and .RData files; it exposes V2 inference and Prometheus metrics endpoints. Building requires Podman, oc, Git, and an image registry, while importing the runtime through the console requires OpenShift AI administrator permissions. The CLI path configures a service account and bearer-token authentication; both example flows send an inference request and show predicted Iris classes. OpenShift supplies Kubernetes deployment functions such as scaling and resource management, while the guide notes UBI images can be scanned for CVEs. The article also describes optional monitoring and pipeline capabilities.

### Source excerpt

Hark, my fellow R programmers, the time is upon us to move out of the workbench, package our glorious models in containers, and send them out into the world! The post Deploy R models on Red Hat OpenShift AI with KServe appeared first on Red Hat Developer.

## Resilience by Design: Protecting Enterprise RAG on Red Hat OpenShift AI

DevFeed: [Resilience by Design: Protecting Enterprise RAG on Red Hat OpenShift AI](<https://devfeed.tech/articles/resilience-by-design-protecting-enterprise-rag-on-red-hat-openshift-ai-119302.md>)

Original publisher: [Read original article](<https://www.veeam.com/blog/rag-backup-openshift-ai.html>)

Author: Jared Matkin

Published: 2026-11-05T07:59:06Z

Content type: article

Language: en

Sources: [Veeam Software Official Blog](<https://devfeed.tech/sources/veeam-software-official-blog.md>)

Topics: [Resilience](<https://devfeed.tech/topics/resilience.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [redhat](<https://devfeed.tech/topics/redhat.md>), [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>), [AI Architecture](<https://devfeed.tech/topics/ai-architecture.md>), [enterprise data protection](<https://devfeed.tech/topics/enterprise-data-protection.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [alliance-partners](<https://devfeed.tech/tags/alliance-partners.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [business](<https://devfeed.tech/tags/business.md>), [data](<https://devfeed.tech/tags/data.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-data](<https://devfeed.tech/tags/enterprise-data.md>), [experimentation](<https://devfeed.tech/tags/experimentation.md>), [generation](<https://devfeed.tech/tags/generation.md>), [kubernetes-backup](<https://devfeed.tech/tags/kubernetes-backup.md>), [openshift](<https://devfeed.tech/tags/openshift.md>), [openshift-ai](<https://devfeed.tech/tags/openshift-ai.md>), [rag](<https://devfeed.tech/tags/rag.md>), [red-hat](<https://devfeed.tech/tags/red-hat.md>), [red-hat-openshift](<https://devfeed.tech/tags/red-hat-openshift.md>), [resilience](<https://devfeed.tech/tags/resilience.md>), [veeam-kasten](<https://devfeed.tech/tags/veeam-kasten.md>)

### AI overview

The Red Hat AI QuickStart demonstrates protecting a RAG application on OpenShift as a coordinated system, including source documents, PostgreSQL/pgvector data, pipelines, model-serving configuration, and Kubernetes resources. Veeam Kasten uses application-aware workflows, including Kanister logical PostgreSQL backups, and can be triggered before ingestion changes the knowledge base, providing a recovery point if an ingestion run fails or corrupts data. The post explains why protecting only the database, object storage, or Kubernetes manifests can leave essential pieces disconnected or missing. Coordinated recovery is presented as a way to reduce manual rebuilding and repeated ingestion work, with workflows for recovery and mobility across compatible namespaces and clusters. The QuickStart is available as a GitHub repository with Helm-based deployment; the text describes a demonstration, not measured recovery outcomes.

### Source excerpt

Generative AI is moving from experimentation to production as organizations build AI assistants, knowledge discovery tools, agentic workflows, and retrieval-augmented generation (RAG) applications that connect large language models to enterprise data. As these systems become business-critical, protecting the data, application state, and dependencies that make them useful has become a fundamental consideration. The post Resilience by Design: Protecting Enterprise RAG on Red Hat OpenShift AI appeared first on Veeam Software Official Blog.

## How Kueue schedules Spark jobs fairly on Red Hat OpenShift AI

DevFeed: [How Kueue schedules Spark jobs fairly on Red Hat OpenShift AI](<https://devfeed.tech/articles/how-kueue-schedules-spark-jobs-fairly-on-red-hat-openshift-ai-116313.md>)

Original publisher: [Read original article](<https://developers.redhat.com/articles/2026/11/04/how-kueue-schedules-spark-jobs-fairly-on-red-hat-openshift-ai>)

Author: Vedant Deshpande

Published: 2026-11-04T13:16:25Z

Content type: article

Language: en

Sources: [Red Hat](<https://devfeed.tech/sources/red-hat.md>), [Red Hat Developer](<https://devfeed.tech/sources/red-hat-developer.md>)

Topics: [kueue](<https://devfeed.tech/topics/kueue.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [Apache Spark](<https://devfeed.tech/topics/spark.md>)

Tags: [admission](<https://devfeed.tech/tags/admission.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [jobs](<https://devfeed.tech/tags/jobs.md>), [kueue](<https://devfeed.tech/tags/kueue.md>), [openshift-ai](<https://devfeed.tech/tags/openshift-ai.md>), [red-hat-openshift](<https://devfeed.tech/tags/red-hat-openshift.md>), [schedules](<https://devfeed.tech/tags/schedules.md>), [spark](<https://devfeed.tech/tags/spark.md>), [spark-operator](<https://devfeed.tech/tags/spark-operator.md>)

### AI overview

Kueue controls when SparkApplications may start by suspending each submission, evaluating its declared CPU and memory against a ClusterQueue, and admitting it to the Spark Operator when quota is available. In the example, a self-managed queue reserves 3 CPUs and 4 GiB: one app with a driver and two executors fits, while a second waits without creating pods and starts after the first finishes. Setup requires the external Red Hat build of Kueue, SparkApplication framework integration and RBAC, a ResourceFlavor/ClusterQueue/LocalQueue, and a queue-name label on every app. The excerpt warns that preemption deletes driver and executor pods without checkpointing, dynamic executor allocation is unsupported, and quota reflects requested rather than actual resource use. It recommends fixed executor counts, explicit resource requests, and checking Workload conditions to distinguish a quota wait from a configuration problem.

### Source excerpt

Table of contents: How Kueue and the Spark Operator divide the work What you will build Set up the integration The post How Kueue schedules Spark jobs fairly on Red Hat OpenShift AI appeared first on Red Hat Developer.

## Benchmarking tiered KV cache offloading on H100 GPUs in OpenShift AI 3.5

DevFeed: [Benchmarking tiered KV cache offloading on H100 GPUs in OpenShift AI 3.5](<https://devfeed.tech/articles/benchmarking-tiered-kv-cache-offloading-on-h100-gpus-in-openshift-ai-3-5-112341.md>)

Original publisher: [Read original article](<https://developers.redhat.com/articles/2026/11/02/benchmarking-tiered-kv-cache-offloading-h100-gpus-openshift-ai-3-5>)

Author: Ramesh Doddaiah, Alberto Perdomo, Nathan Scott, Ashish Kamra, Naina Singh

Published: 2026-11-02T14:17:22Z

Content type: news

Language: en

Sources: [Red Hat](<https://devfeed.tech/sources/red-hat.md>), [Red Hat Developer](<https://devfeed.tech/sources/red-hat-developer.md>)

Topics: [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [Cache](<https://devfeed.tech/topics/cache.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [Multi-GPU](<https://devfeed.tech/topics/multi-gpu.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-inference](<https://devfeed.tech/tags/ai-inference.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [cache](<https://devfeed.tech/tags/cache.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [kv-cache](<https://devfeed.tech/tags/kv-cache.md>), [offloading](<https://devfeed.tech/tags/offloading.md>), [openshift](<https://devfeed.tech/tags/openshift.md>), [openshift-ai](<https://devfeed.tech/tags/openshift-ai.md>)

### AI overview

In Red Hat OpenShift AI 3.5 tests on H100 GPUs, tiered KV cache offloading improved long-context inference most when the reusable working set exceeded CPU cache capacity. For Nemotron-Ultra-253B, adding NVMe or CephFS to CPU offload raised throughput from 0.44 to about 0.76-0.77 requests/s and cut mean TTFT from about 60 seconds without offload to 9.6 seconds; CPU alone reached 0.44 requests/s. Qwen's working set fit in CPU memory, so CPU offload captured most gains, while secondary storage added about 10% in a single-replica test. Gemma's gains were limited by GPU memory utilization. Local NVMe had the lowest storage latency and suits single-node locality; CephFS adds latency but offers shared capacity and cross-replica cache reuse, especially as concurrency rises. The results used CephFS with a single data copy, so affected entries would need recomputation after OSD loss. The article recommends measuring block-sized storage p99 latency, estimating the restore-versus-recompute crossover, then validating candidate tiers against representative traces and concurrency.

### Source excerpt

Long-context workloads are quickly becoming the norm for enterprise AI. Agentic applications carry an ever-growing history of tool calls and intermediate results, retrieval-augmented generation prepends thousands of tokens of retrieved context, and multi-turn assistants resend the whole conversation with every turn. In all of these cases, the model sees large parts of the same prompt again and again. The post Benchmarking tiered KV cache offloading on H100 GPUs in OpenShift AI 3.5 appeared first on Red Hat Developer.