# Red Hat Developer Stories and tutorials on the latest technologies in cloud application development. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## From hours to minutes: Optimizing Red Hat Developer Hub performance testing with immutable LDAP images DevFeed: [From hours to minutes: Optimizing Red Hat Developer Hub performance testing with immutable LDAP images]() Original publisher: [Read original article]() Author: Shashank Kestwal Published: 2026-09-17T13:16:48Z Content type: article Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Performance Testing](), [LDAP](), [Keycloak](), [CI/CD](), [Concurrency](), [Deployment](), [rbac]() Tags: [ci-cd](), [concurrency](), [deployment](), [keycloak](), [ldap](), [migration](), [performance-testing](), [testing]() ### AI overview This Red Hat developer article describes a performance-testing bottleneck in Red Hat Developer Hub caused by generating users and groups at runtime through the Keycloak Admin REST API and synchronizing them over HTTP. It introduces pre-built LDAP container images as immutable infrastructure to reduce environment setup complexity and improve testing feedback loops. ### Source excerpt At Red Hat, our CI/CD pipelines are the heartbeat of our development process. However, as we scaled the Red Hat Developer Hub performance testing framework, we hit a wall. Our environment setup time was ballooning, turning what should have been a seamless verification step into a long waiting game. For performance engineering in catalog-dependent applications, deployment and catalog population speed directly dictate your feedback loops. The post From hours to minutes: Optimizing Red Hat Developer Hub performance testing with immutable LDAP images appeared first on Red Hat Developer. ## Catching poor LLM performance and accuracy before deployment DevFeed: [Catching poor LLM performance and accuracy before deployment]() Original publisher: [Read original article]() Author: Christopher Miyai Published: 2026-09-17T13:16:47Z Content type: article Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [vllm](), [Inference Performance](), [LLM evaluation / benchmarking](), [benchmarking](), [CI/CD](), [model-deployment](), [Open Source](), [container]() Tags: [ai-inference](), [benchmarking](), [benchmarks](), [ci-cd](), [container-images](), [deployment](), [developer-tools](), [llm](), [open-source](), [performance](), [vllm]() ### AI overview This article describes a regression-testing system for Red Hat AI Inference that compares upstream and midstream vLLM builds. It benchmarks LLM performance and accuracy across hardware variants and uses CI/CD to detect regressions before release. ### Source excerpt vLLM is the leading open source inference and serving engine for LLMs. Averaging 64 commits a day with bi-weekly releases, the open source project goes through a significant amount of code changes rapidly. Red Hat AI Inference offers an integrated inference platform powered by vLLM, llm-d and vLLM's llm-compressor. The post Catching poor LLM performance and accuracy before deployment appeared first on Red Hat Developer. ## Build a unified CI/CD control plane with Red Hat Developer Hub DevFeed: [Build a unified CI/CD control plane with Red Hat Developer Hub]() Original publisher: [Read original article]() Author: Rishabh Singh Published: 2026-09-17T13:16:44Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [internal developer portal](), [Backstage](), [argo-cd](), [CI/CD](), [Platform Engineering]() Tags: [argo-cd](), [backstage](), [ci-cd](), [cognitive-load](), [developer-portal](), [developer-productivity](), [guide](), [how-to](), [onboarding](), [openshift](), [platform](), [platform-engineering]() ### AI overview This guide explains how platform engineers can deploy and configure Red Hat Developer Hub as a unified developer portal for Red Hat OpenShift, Argo CD, Tekton, Quay, and related deployment information. It describes aggregating pipeline runs, deployment health, and container image tags in one view, along with software templates for self-service project bootstrapping. ### Source excerpt If your engineering teams waste time context-switching between Red Hat OpenShift, Argo CD, Tekton, and Quay, your platform needs a unified developer portal. The post Build a unified CI/CD control plane with Red Hat Developer Hub appeared first on Red Hat Developer. ## Why Kafka retention.ms can delay message deletion DevFeed: [Why Kafka retention.ms can delay message deletion]() Original publisher: [Read original article]() Author: Rogerio Santos Published: 2026-09-16T13:05:06Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Kafka](), [Apache-Kafka](), [configuration](), [file](), [Event-Streaming]() Tags: [broker](), [configuration](), [diagnose](), [event-driven](), [how-to](), [kafka](), [lifecycle](), [retention](), [storage](), [stream-processing]() ### AI overview This guide explains why Kafka messages can remain readable beyond a topic's retention.ms setting. Kafka deletes closed log segments rather than individual messages, and the active segment and continuous writes can delay removal of older records. ### Source excerpt A customer opened a support case with a deceptively simple complaint: a Kafka topic was configured with a 12-hour retention (retention.ms), yet messages produced on July 24 were still readable 4 days later, on July 28. Nothing was broken. The broker logged no errors. The retention policy was working as designed, but the segment layout and continuous write pattern delayed when the old records could actually be removed. The post Why your Kafka topic ignores retention.ms (and how to fix it) appeared first on Red Hat Developer. ## Constraining AI agents with Red Hat AI: Containment, identity, and governance DevFeed: [Constraining AI agents with Red Hat AI: Containment, identity, and governance]() Original publisher: [Read original article]() Author: Grace Ableidinger Published: 2026-09-16T13:01:59Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Artificial Intelligence](), [Security](), [Zero Trust](), [Containers](), [Kubernetes](), [Architecture & Design]() Tags: [ai](), [ai-agents](), [containers](), [deployment](), [kubernetes](), [prompt-injection](), [security](), [trust]() ### AI overview This tutorial explains how to secure AI agents running on Red Hat OpenShift using containment, verifiable identity, and governance. It covers namespace isolation, quotas, sandboxing, workload identity, and admission control, with OpenClaw used in the demo. ### Source excerpt When an agent process runs on your laptop, it typically inherits anything your user has access to. Often this includes the full network stack, the file system, and the credentials sitting in memory. When integrating with GitHub, Slack, or a cloud provider, you could be one faulty permission or well-crafted prompt injection away from a security incident. The post Constraining AI agents with Red Hat AI: Containment, identity, and governance appeared first on Red Hat Developer. ## Red Hat Developer Hub: Preventing compliance violations with AI coding agents DevFeed: [Red Hat Developer Hub: Preventing compliance violations with AI coding agents]() Original publisher: [Read original article]() Author: Evan Shortiss, Ben Wilcock Published: 2026-09-15T13:17:13Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [internal developer portal](), [AI-assisted coding](), [Backstage](), [Claude Code](), [Command-line interface](), [Model Context Protocol](), [Security]() Tags: [ai-coding-agents](), [ai-inference](), [backstage](), [catalog](), [claude-code](), [cli](), [developer](), [developer-productivity](), [developer-tools](), [mcp](), [platform-engineering](), [security]() ### AI overview This tutorial demonstrates how an AI coding agent connected to Red Hat Developer Hub can query a Backstage software catalog, TechDocs, and software templates before making architectural decisions. Using a simulated insurance-company catalog, the demo shows how this context can help avoid PCI-DSS compliance violations, resolve governance conflicts, and create a traceable decision record. ### Source excerpt AI coding agents can generate entire services, reason about architectures, and scaffold applications in minutes. But ask one to build a service for your organization and you'll quickly notice the gap: it doesn't know your rules. It doesn't know which messaging broker your compliance team mandates, which services already exist in adjacent domains, or which project template is the golden path for your team. The post Red Hat Developer Hub: Preventing compliance violations with AI coding agents appeared first on Red Hat Developer. ## Understanding W8A8 INT8 LLM quantization: Accuracy and performance results DevFeed: [Understanding W8A8 INT8 LLM quantization: Accuracy and performance results]() Original publisher: [Read original article]() Author: Sana Fayyaz Published: 2026-09-14T13:01:43Z Content type: article Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Large Language Model](), [quantization](), [llama](), [Compression](), [Benchmark](), [dataset](), [Algorithms]() Tags: [ai-inference](), [artificial-intelligence](), [benchmark](), [benchmarks](), [compression](), [evaluation](), [hardware](), [llama](), [llm](), [model](), [models](), [performance](), [quantization](), [reasoning](), [zero-shot]() ### AI overview The article evaluates W8A8 INT8 quantization of a Llama 3.1 8B Instruct model. It describes reducing the model from 14.9 GB to 8.0 GB with SmoothQuant and GPTQ, then compares the base and compressed models on four benchmarks to assess accuracy and performance. ### Source excerpt In Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy, we compressed a Llama 3.1 8B Instruct model from 14.9 GB to 8.0 GB using 8-bit integer (INT8) W8A8 quantization with SmoothQuant and Generative Pre-trained Transformer Quantization (GPTQ). The post Understanding W8A8 INT8 LLM quantization: Accuracy and performance results appeared first on Red Hat Developer. ## Python 3.14 free-threaded build is now available in RHEL DevFeed: [Python 3.14 free-threaded build is now available in RHEL]() Original publisher: [Read original article]() Author: Lumír Balhar Published: 2026-09-14T13:01:41Z Content type: release Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Python 3.14](), [Python](), [Concurrency](), [Linux](), [Concurrent Programming](), [cpu]() Tags: [cpu](), [developer-tools](), [developers](), [linux](), [performance](), [programming-languages-frameworks](), [python](), [python-3-14](), [red-hat](), [release](), [rhel](), [thread](), [upstream-release]() ### AI overview Red Hat Enterprise Linux 9.8 and 10.2 now provide a free-threaded Python 3.14 build through the Red Hat CodeReady Linux Builder repositories. With the GIL disabled, CPU-bound Python threads can execute in parallel across multiple CPU cores within a single process. The article explains expected performance benefits, installation, verification, and possible thread-safety issues in existing code. ### Source excerpt Developers on Red Hat Enterprise Linux 9.8 and 10.2 can now test full parallel CPU execution in Python using the new free-threaded Python 3.14 build. In addition to the regular Python 3.14 interpreter, we also provide the free-threaded variant in the Red Hat CodeReady Linux Builder repositories. Python 3.14 is the first upstream release where the free-threaded build is officially supported rather than experimental. The post Python 3.14 free-threaded build is now available in RHEL appeared first on Red Hat Developer. ## Unlock a LUKS root over SSH on Fedora and Red Hat Enterprise Linux DevFeed: [Unlock a LUKS root over SSH on Fedora and Red Hat Enterprise Linux]() Original publisher: [Read original article]() Author: Josephine Pfeiffer Published: 2026-09-11T13:01:51Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Fedora](), [Linux](), [OpenSSH](), [ssh](), [systemd](), [datacenter](), [Network](), [Server]() Tags: [config](), [datacenter](), [developer](), [how-to](), [linux](), [network](), [red-hat](), [remote](), [rhel](), [server](), [ssh](), [systemd]() ### AI overview This tutorial explains how to unlock an encrypted LUKS root remotely over SSH on Fedora and Red Hat Enterprise Linux. It describes adding NetworkManager and an SSH server to the dracut initramfs, configuring networking, rebuilding the initramfs, and using the rd.neednet=1 kernel argument. ### Source excerpt An encrypted server in a datacenter reboots and stops in the initramfs, waiting for a passphrase at a console nobody is sitting at. 3 commands and a kernel argument get NetworkManager and sshd into a Fedora or Red Hat Enterprise Linux (RHEL) initramfs, so a remote server with an encrypted root can be unlocked over the network. The post Unlock a LUKS root over SSH on Fedora and Red Hat Enterprise Linux appeared first on Red Hat Developer. ## Bringing custom knowledge to agents with AutoRAG DevFeed: [Bringing custom knowledge to agents with AutoRAG]() Original publisher: [Read original article]() Author: Diego Alvarez Ponce, Diego Garcia Perez Published: 2026-09-11T13:01:50Z Content type: article Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Retrieval Augmented Generation (RAG)](), [Model Context Protocol (MCP)](), [Databases](), [Large Language Model](), [AI Development](), [LLM evaluation / benchmarking]() Tags: [ai](), [ai-inference](), [artificial-intelligence](), [database](), [developer](), [generative-ai](), [gpu](), [guide](), [how-to](), [large-language-models-llms](), [model-context-protocol-mcp](), [rag](), [red-hat](), [terminal]() ### AI overview This guide explains how to use AutoRAG in Red Hat OpenShift AI to optimize retrieval-augmented generation for enterprise, domain-specific data. It also shows how to integrate a Model Context Protocol server that retrieves customer information from an internal database, using a fictional banking scenario. ### Source excerpt The large language models (LLMs) that power generative AI work by drawing upon the patterns and information present in their training data. Without access to the right data, LLMs struggle to comprehend context--like our internal corporate vocabulary--and as a result, start to hallucinate. The post Bringing custom knowledge to agents with AutoRAG appeared first on Red Hat Developer. ## Red Hat edge platforms: Choosing the right one for your use case DevFeed: [Red Hat edge platforms: Choosing the right one for your use case]() Original publisher: [Read original article]() Author: Daniel Froehlich Published: 2026-09-11T13:01:48Z Content type: article Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Edge](), [Containers](), [Kubernetes](), [Architecture & Design](), [Hardware](), [Availability](), [Microservice]() Tags: [containers](), [deployment](), [edge](), [edge-computing](), [hardware](), [high-availability](), [kubernetes](), [management-tools](), [microservices](), [red-hat](), [virtual-machines]() ### AI overview This article introduces a series about choosing Red Hat edge platforms for specific deployment needs. It compares Red Hat Enterprise Linux and Red Hat OpenShift across workload types, platform sizes, hardware requirements, Kubernetes use cases, availability, storage, and management needs. ### Source excerpt Choosing the right platform for an edge deployment is one of the most consequential decisions an organization makes--and one of the most confusing. The options range from a single-board computer running a handful of containers to a full Kubernetes cluster with high availability, software-defined storage, and centralized management. Pick too small, and you hit a wall when requirements grow. The post Red Hat edge platforms: Choosing the right one for your use case appeared first on Red Hat Developer. ## From token consumer to token provider: Building your org's AI API DevFeed: [From token consumer to token provider: Building your org's AI API]() Original publisher: [Read original article]() Author: Markell Rawls Published: 2026-09-10T13:01:50Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Artificial Intelligence](), [API](), [API keys](), [AI Infrastructure](), [Security](), [NVIDIA DGX](), [vllm](), [Claude Code](), [hugging face](), [anthropic](), [OpenAI]() Tags: [ai](), [ai-inference](), [ai-infrastructure](), [api](), [api-keys](), [claude](), [claude-code](), [developer](), [gpu](), [hugging-face](), [openai](), [security](), [vllm]() ### AI overview The article describes how organizations can move from independently purchasing AI-provider access and distributing API keys toward centrally managing AI infrastructure and providing internal AI APIs. It highlights rising token costs, fragmented workloads, limited visibility, and security-audit difficulties. ### Source excerpt One of the biggest problems with AI right now is that it's expensive. If you've been anywhere near an enterprise IT budget in the last 2 years, then you already know that. Most companies that wanted to get AI into their workflows did the same thing: They signed up for a business account with an AI provider, handed out API keys, and started building. It made sense at the time because the models were good, the APIs were simple, and the alternative was standing up your own inference infrastructure, which nobody had bandwidth for. But then the bills started coming in. The post From token consumer to token provider: Building your org's AI API appeared first on Red Hat Developer. ## Deploy NeMo Guardrails on Red Hat OpenShift AI DevFeed: [Deploy NeMo Guardrails on Red Hat OpenShift AI]() Original publisher: [Read original article]() Author: Rob Geada Published: 2026-09-09T15:05:01Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [NeMo](), [Deployment](), [ai safety](), [Open Source](), [prompt injection]() Tags: [article](), [deployment](), [developer](), [how-to](), [nemo](), [open-source](), [operator](), [platform](), [prompt-injection](), [red-hat](), [safety](), [security]() ### AI overview This tutorial explains how to deploy an evaluated NeMo Guardrails configuration on a Red Hat OpenShift AI cluster. It covers prerequisites, creating a ConfigMap from the configuration files, and creating a NeMoGuardrails custom resource for a managed deployment. ### Source excerpt This is part 3 in a 3-part series on local guardrail development and evaluation. In the 1st article, I looked at how to design and develop a guardrail configuration on a local machine, and then tried some manual testing. In the 2nd article, I explored how to rigorously test a guardrail against popular large-scale risk datasets. The post Deploy NeMo Guardrails on Red Hat OpenShift AI appeared first on Red Hat Developer. ## Use a local and open source code assistant DevFeed: [Use a local and open source code assistant]() Original publisher: [Read original article]() Author: Seth Kenlon Published: 2026-09-09T14:01:45Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [ai-coding](), [Local AI](), [Open Source Models & Datasets](), [Large Language Model](), [Model Context Protocol](), [ide](), [Security, Privacy and Abuse Prevention](), [Command-line interface](), [Homebrew](), [Linux](), [macOS]() Tags: [ai-coding](), [ai-inference](), [artificial-intelligence](), [command-line](), [developer-tools](), [ide](), [linux](), [llm](), [local-ai](), [macos](), [model-context-protocol](), [ollama](), [open-source](), [privacy]() ### AI overview This Red Hat Developer article explains how to use OpenCode as a local, open source AI coding assistant. It covers OpenCode's terminal, desktop, and IDE extension interfaces, its use of the Model Context Protocol, installation requirements, and the need to configure an LLM. For privacy-conscious local development, it recommends open source local AI tools such as Ollama or OpenVINO. ### Source excerpt There's a lot of excitement about AI coding assistants, but many of the available options either aren't open source, or don't respect your data privacy by sending what you're working on to the cloud for processing. If you're looking for an alternative to closed AI, then you need an open coding assistant and an open source IDE. The post Use a local and open source code assistant appeared first on Red Hat Developer. ## Personalize your product's text-to-speech voice for any language: Fine-tuning with Kubeflow Trainer on Red Hat OpenShift AI DevFeed: [Personalize your product's text-to-speech voice for any language: Fine-tuning with Kubeflow Trainer on Red Hat OpenShift AI]() Original publisher: [Read original article]() Author: Dmytro Hryshchenko, Abhijeet Dhumal Published: 2026-09-09T03:32:28Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [Fine-tuning](), [voice ai](), [Training AI Models](), [Artificial Intelligence](), [distributed-training](), [GPU](), [lora](), [data](), [Open Source]() Tags: [ai](), [artificial-intelligence](), [distributed-training](), [fine-tuning](), [gpu](), [lora](), [open-source](), [speech](), [text-to-speech](), [training](), [voice](), [workflow]() ### AI overview This tutorial explains how to fine-tune the open source Orpheus-3B text-to-speech model for Turkish using Red Hat OpenShift AI and Kubeflow Trainer. It describes packaging distributed training in a TrainJob, scaling across nodes and GPUs, and using LoRA to keep memory usage below 16 GB. The reported result reduces speech errors by more than 90% compared with the base model. ### Source excerpt Can't Read, Won't Buy. That is the title CSA Research gave its survey of 8,709 consumers across 29 countries, and the numbers justify it: 76% prefer to buy in their own language, and 40% will never buy in another. The same rule governs what your product says out loud. The post Personalize your product's text-to-speech voice for any language: Fine-tuning with Kubeflow Trainer on Red Hat OpenShift AI appeared first on Red Hat Developer. ## Optimize vLLM speculative decoding with FastMTP heads DevFeed: [Optimize vLLM speculative decoding with FastMTP heads]() Original publisher: [Read original article]() Author: Rahul Tuli Published: 2026-09-08T14:20:16Z Content type: article Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [vllm](), [Inference](), [Large Language Model](), [Fine-tuning](), [model-deployment](), [deepseek](), [qwen]() Tags: [ai-inference](), [artificial-intelligence](), [data](), [deepseek](), [developer-tools](), [fine-tuning](), [hardware](), [inference](), [large-language-model](), [production](), [qwen](), [tokens](), [vllm]() ### AI overview This article explains how FastMTP-style fine-tuning improves vLLM speculative decoding. It describes using native multi-token prediction heads as speculators, adapting a single head for recursive multi-step drafting, extracting weights from verifier checkpoints, and producing vLLM-ready checkpoints without training from scratch. ### Source excerpt Autoregressive decoding makes large language model (LLM) inference memory-bandwidth bound: every token needs 1 full forward pass over billions of parameters, so the hardware spends most of its time moving weights rather than computing. MTP is a training objective: models like the DeepSeek and Qwen families learn to predict several future tokens at each position, which improves their data efficiency and quality. The post Optimize vLLM speculative decoding with FastMTP heads appeared first on Red Hat Developer. ## Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy DevFeed: [Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy]() Original publisher: [Read original article]() Author: Sana Fayyaz Published: 2026-09-07T07:01:34Z Content type: article Language: en Sources: [Red Hat Developer]() Topics: [quantization](), [Large Language Model](), [GPU](), [Inference](), [model-deployment](), [Post-training optimization](), [llama](), [LLM Techniques]() Tags: [ai-inference](), [artificial-intelligence](), [compression](), [deployment](), [gpu](), [inference](), [language-models](), [large-language-models](), [llama](), [llm](), [memory](), [performance](), [post-training](), [quantization]() ### AI overview This article explains INT8 W8A8 quantization for Llama 3.1 8B using SmoothQuant and GPTQ. It describes how quantization reduces memory requirements and can improve serving performance while preserving model accuracy, including a reported 46% reduction in model size and planned benchmark testing with vLLM and llm-compressor. ### Source excerpt Large language models are expensive to serve. A model like Llama 3.1 8B in Bfloat16 (BF16) precision occupies roughly 15 GB of GPU memory. In BF16, each of the 8 billion parameters takes 2 bytes to store, which adds up to roughly 15 GB for the weights--and that's not all. The GPU needs memory for the key-value (KV) cache to store context for active requests, alongside intermediate tensor outputs (activations, as we call them) generated during inference. The post Understanding W8A8 INT8 LLM quantization: Half the size, better performance, same accuracy appeared first on Red Hat Developer. ## Red Hat Developer Hub software template authoring with rhdh-templates DevFeed: [Red Hat Developer Hub software template authoring with rhdh-templates]() Original publisher: [Read original article]() Author: Kashish Mittal Published: 2026-09-07T07:01:32Z Content type: tutorial Language: en Sources: [Red Hat Developer]() Topics: [Backstage](), [internal developer portal](), [Nunjucks](), [AI-assisted coding](), [YAML]() Tags: [ai-coding-agents](), [artificial-intelligence](), [backstage](), [developer-portal](), [developer-productivity](), [developer-tools](), [platform-engineering](), [quick-start](), [red-hat](), [software-templates](), [terminal](), [validation]() ### AI overview This tutorial introduces the rhdh-templates skill for building Red Hat Developer Hub and Backstage software templates with an AI coding assistant. It covers Nunjucks conventions, YAML schema checking, reference templates, local offline validation, repository templatization, and optional testing against a Red Hat Developer Hub instance. ### Source excerpt If you are a platform engineer or developer building Red Hat Developer Hub software templates, you know the friction of wrestling with Nunjucks syntax, guessing location.yaml placements, and discovering errors only after rendering in your developer portal. While AI coding agents handle generic YAML, they lack Red Hat Developer Hub and Backstage-specific conventions. The post Red Hat Developer Hub software template authoring with rhdh-templates appeared first on Red Hat Developer.