2026-06-30 07:01
🚀 In the final part of our series, we explore secure agentic AI using Red Hat OpenShift AI and EnterpriseDB. We dive into the Model Context Protocol (MCP), which standardizes tool integration and enhances user experience through event streaming. Key security and performance tuning practices are discussed to ensure safe deployment of stochastic reasoning engines. Learn how MCP enables seamless interaction between the orchestrator and servers, improving efficiency while maintaining security. 🔒...
Source: Red Hat Developer Blog
Peter Samouelian
2026-06-30 03:01
Unlock the potential of Red Hat OpenShift Virtualization with effective ServiceNow CMDB discovery! This article guides you through creating a clean inventory of virtual machines (VMs) by defining a custom CI class and implementing a tailored Discovery pattern. Key steps include: 1️⃣ Establishing a custom CI class for OpenShift VMs. 2️⃣ Setting identification rules to reduce clutter. 3️⃣ Scheduling and validating your discovery process. Ensure your CMDB is streamlined and efficient! #RedHat...
Source: Red Hat Developer Blog
Moyo Oyegunle
2026-06-30 03:01
Setting up OpenShift Virtualization with ServiceNow CMDB discovery involves deploying an in-cluster MID Server. This process ensures that virtual machines are visible to IT teams and can be managed effectively. Stock ServiceNow Kubernetes discovery pulls in too much data, missing the proper classification for KubeVirt VMs. A custom discovery pattern is needed to resolve this. Key steps include creating a least-privilege service account, deploying a CA-trusted MID server, and ensuring secure...
Source: Red Hat Developer Blog
Moyo Oyegunle
2026-06-29 14:15
🚀 Building a dynamic E2E test quarantine system can significantly enhance your CI process. This guide outlines the steps to create an automated quarantine system using Prometheus and Grafana. It allows for continuous monitoring of test health, automated quarantine decisions, and Jira ticket integration. Key steps include deploying Prometheus for test analytics and configuring Grafana for visualization. The system ensures that flaky tests are managed effectively, reducing developer effort. 🔍...
Source: Red Hat Developer Blog
Denis Moskalenko
2026-06-29 07:01
🚀 Implementing GPU-as-a-Service (GPUaaS) can help organizations optimize GPU utilization by allowing developers to reserve GPU slices on demand, much like booking a meeting room. This approach uses Red Hat OpenShift, Kueue, and NVIDIA Multi-Instance GPU (MIG) to manage shared resources effectively. With this system, developers can access GPU resources easily, reducing idle time and improving efficiency. Explore how GPUaaS can transform your AI workloads! 💻🔍 #GPUaaS #RedHat #NVIDIA #AI...
Source: Red Hat Developer Blog
Cedric Clyburn, James Harmison
2026-06-29 07:01
🔍 Exploring Red Hat UBI vs. Hardened Images? Both Red Hat Universal Base Image (UBI) and Hardened Images are available for developers to create and share container images without Red Hat restrictions. The choice depends on your priorities: UBI offers development stability and formal certifications, while Hardened Images focus on security and a minimal attack surface. For more insights on their differences and use cases, check out the full article! #RedHat #ContainerImages #UBI #HardenedImages...
Source: Red Hat Developer Blog
Fernando Lozano
2026-06-26 07:01
🚀 Exploring distributed AI inference? This article outlines essential blueprints for various traffic shapes, from high-concurrency chat to edge inference on workstations. Each blueprint includes a workload signature, KPI priority, and topology details. It also covers troubleshooting strategies for optimizing performance metrics like TTFT and TPOT. A step-by-step growth path is provided for teams scaling from a single vLLM instance. Dive into the mechanics of AI deployment! 💻📊 #AI...
Source: Red Hat Developer Blog
Fatih E. Nar, Yuchen Fama, Greg Pereira, Yuan Tang
2026-06-25 07:15
Explore the engineering behind the Data Governance Copilot in Part 3 of our series! This article details the copilot's container-level architecture, highlighting the use of high-level frameworks like Llama Stack versus lower-level Python libraries. It also covers the mechanics of formatting LLM messages and the user query flow. Stay tuned for more on integrating OpenShift AI and PG Airman MCP! 🚀🔍 #DataGovernance #OpenShiftAI #AIIntegration #TechArchitecture #MachineLearning
Source: Red Hat Developer Blog
Peter Samouelian
2026-06-25 07:15
🚀 Building a consistent RHEL environment is essential for maintaining operational stability. Red Hat's image builder and Lightspeed content templates streamline this process. 🔧 The image builder allows for customized image creation, while content templates ensure standardized package management. This leads to consistent deployments and updates across your systems. 📋 The process involves creating a content template, building an image blueprint, deploying the system, and updating templates as...
Source: Red Hat Developer Blog
Shane McDowell
2026-06-25 07:15
🚀 Exciting updates are here for the cert-manager operator on Red Hat OpenShift! Version 1.19 introduces the trust-manager, allowing admins to customize and distribute trusted CA bundles across Kubernetes clusters. This upgrade enhances automated management of TLS certificates and builds the foundation for mutual TLS (mTLS) security. By efficiently managing certificate lifecycles, teams can adopt zero trust principles, ensuring secure communication between workloads. 🔗 Explore the benefits of...
Source: Red Hat Developer Blog
Nick Png
2026-06-25 03:01
Struggling with Python dependency trees? 🐍 Fromager simplifies building from source by generating two key artifacts: build-order.json and graph.json. These tools ensure reproducibility and auditability—critical for secure environments like finance and regulated AI. It addresses common issues with pip, such as circular dependencies and lack of customization for build flags. Learn more about how Fromager can enhance your Python projects! 📦🔍 #Python #Fromager #DependencyManagement #OpenSource...
Source: Red Hat Developer Blog
Lalatendu Mohanty, Rohan Devasthale
2026-06-24 07:16
Optimizing distributed AI inference involves key strategies to enhance performance. The article discusses three main optimization levers: 1. Prefill/decode disaggregation. 2. Key-value (KV) cache strategy. 3. Speculative decoding. These strategies aim to improve cost, latency, and throughput based on specific deployment needs. Effective implementation can lead to significant cost savings, particularly in high-demand environments. For more insights, check the full article! 🧠💻📊 #AI...
Source: Red Hat Developer Blog
Fatih E. Nar, Yuchen Fama, Greg Pereira, Yuan Tang
2026-06-24 07:16
Unlocking the potential of static application security testing (SAST) is crucial for development efficiency. The SastAI initiative at Red Hat, in partnership with NVIDIA, aims to automate the identification of false positives using generative AI. 🤖 Through a multi-stage workflow, SastAI analyzes SAST findings and leverages pattern harvesting to enhance triage efficiency, reducing noise and improving accuracy. 📊 The project utilizes a robust dataset and strategic sampling to ensure quality...
Source: Red Hat Developer Blog
Itay Krispin, Guy Ziv
2026-06-24 07:16
🚀 Learn how to build a customized Red Hat Enterprise Linux EUS image using the image-builder CLI! This guide covers prerequisites, including the need for a running RHEL instance. It details defining a repository configuration and creating a blueprint to customize your image. Follow the steps to set up your image, ensuring it supports Extended Update Support for RHEL 9.6. 🔧 #RedHat #Linux #ImageBuilder #EUS #TechGuide
Source: Red Hat Developer Blog
Justin Sherrill
2026-06-23 07:01
🔗 Connect EvalHub to your protected model servers! This guide details how to configure your EvalHub runtime for both internal and external model servers. It covers the use of service account tokens, API keys, and custom certificates to ensure secure connections. For a successful evaluation job, the correct authentication method is crucial, especially in production environments. Learn more about securing your AI evaluation infrastructure! #AI #EvalHub #MachineLearning #DataSecurity #RedHatAI
Source: Red Hat Developer Blog
Sobha Cheruku, Prabhu Padashetty, Narayan Sagar, Gin Biak Naulak
2026-06-23 07:01
🚀 Building a custom Red Hat Enterprise Linux kernel for the NVIDIA DGX Spark platform requires specific steps. This guide details how to compile the RHEL 10 kernel and NVIDIA GPU driver from source. It outlines prerequisites, including the need for an ARM64 system or DGX Spark Founder's Edition. 🔧 Developers should note this is a Developer Preview, not intended for production use. For full instructions, see the guide! #NVIDIA #RedHat #Linux #Kernel #DGXSpark
Source: Red Hat Developer Blog
Micah Abbott, Henry Geay de Montenon, Jiri Benc
2026-06-22 15:25
Explore how SQL and GenAI can transform data management with Apache Iceberg on Red Hat OpenShift! This article discusses using Trino's AI functions to connect lakehouse architecture with LLM models—all through SQL. Analysts can join data sources, run analyses, and generate insights without complex setups. Key features include AI functions for sentiment analysis, classification, and text generation directly from SQL, streamlining workflows and enhancing data-driven decisions. Get started with...
Source: Red Hat Developer Blog
Mike Hepburn
2026-06-22 14:26
🚀 Red Hat Advanced Cluster Management for Kubernetes 2.17 introduces developer preview for right-sizing recommendations using Perses dashboards. This update enhances visualization by migrating from Grafana to a more modular, code-defined solution. Key features include native Kubernetes integration and seamless console navigation. Namespace and OpenShift Virtualization right-sizing are covered, offering detailed insights into resource allocation. Explore these new capabilities and optimize...
Source: Red Hat Developer Blog
Darshan Vandra, Raj Zalavadia
2026-06-22 07:01
Choosing the right model-serving engine like vLLM is just the starting point for enterprise AI inference. This article emphasizes the importance of understanding the core concepts of inference, the prefill and decode phases, and the dimensions of parallelism necessary for effective deployment. Key performance indicators (KPIs) such as time to first token (TTFT) and throughput are crucial for adapting to specific workloads. Recent developments include improved KV cache management and the shift...
Source: Red Hat Developer Blog
Fatih E. Nar, Yuchen Fama, Greg Pereira, Yuan Tang
2026-06-22 07:01
🚀 Red Hat Enterprise Linux has introduced a new feature in Identity Management: system accounts. This allows fine-grained access control for user accounts while enhancing security. 🔑 A key use case is enabling password rotation for regular users, addressing past challenges with static passwords. CyberArk now integrates with this feature, allowing seamless password management for organizations. 💻 The sysaccounts feature bypasses common constraints, enhancing automation in password management...
Source: Red Hat Developer Blog
Josep Andreu Font, Francisco Trivino Garcia
2026-06-19 07:16
🚀 Exciting developments in AI memory management! The article discusses deploying MemPalace's Model Context Protocol (MCP) server on Red Hat OpenShift AI, addressing the issue of lost context in AI conversations. MemPalace organizes memory hierarchically, improving recall and debugging. Key points include: - An HTTP/WebSocket wrapper for Kubernetes compatibility. - Health probes for better service management. - Compliance with OpenShift Security Context Constraints. This guide is valuable for...
Source: Red Hat Developer Blog
Gerald Trotman
2026-06-19 07:16
🚀 Red Hat Ansible Automation Platform 2.7 is now available! This release offers flexible installation methods for Red Hat Enterprise Linux (RHEL) and OpenShift. Key features include a containerized installer and two deployment topologies: Growth and Enterprise for RHEL, and Operator Growth and Enterprise for OpenShift. Upgrading from version 2.6 is supported, but users with RPM-based deployments must migrate to the containerized installer first. Learn more about the new features and...
Source: Red Hat Developer Blog
Catherine Choi
2026-06-18 14:00
🚀 EvalHub is transforming LLM evaluation in Kubernetes. As AI/ML workloads grow, managing resources becomes critical. Kueue addresses this by providing a structured queueing system for workload management. It ensures fair resource sharing, prioritization of urgent jobs, and minimizes operational inefficiencies. This guide is part of a series on building a scalable AI evaluation infrastructure. #AI #Kubernetes #EvalHub #MachineLearning #WorkloadManagement
Source: Red Hat Developer Blog
Narayan Sagar, Prabhu Padashetty, Sobha Cheruku, Gin Biak Naulak
2026-06-18 14:00
🔍 After an OpenShift upgrade, diagnosing application misbehavior is crucial. This article highlights key areas to investigate: 1️⃣ **Migration Issues**: Upgrades usually don’t require application changes if compatible with cgroups v1 or v2. 2️⃣ **Troublesome Scenarios**: Changes in application images, workloads, or instrumentation can lead to unexpected behavior. 3️⃣ **Container Awareness**: Applications must recognize container limits to function correctly. Non-container-aware applications...
Source: Red Hat Developer Blog
Francisco De Melo Junior
2026-06-18 07:01
🚀 Embrace CI/CD with Red Hat OpenShift Pipelines! Built on Tekton, it allows for efficient execution of cloud-native pipelines. However, high-churn environments lead to fleeting logs, making observability a challenge. 🛠️ The Red Hat build of OpenTelemetry addresses this by capturing and routing pipeline logs for both local troubleshooting and long-term storage in Splunk-HEC, ensuring compliance with industry regulations. 🔍 Enhance your logs with vital metadata and maintain easy access to...
Source: Red Hat Developer Blog
Michaela Lang
2026-06-17 14:01
🚀 Red Hat build of Apache Camel 4.18 enhances integration with AI-driven semantic processing. Key updates include: 🔧 Major upgrades to the Kaoto design suite and a new Camel CLI Launcher streamline development. 📦 New support for components like camel-openai for OpenAI integrations and camel-docling for document processing. 🔄 This release is the last on Spring Boot 3, with a planned transition to Spring Boot 4 later this year. Explore more about the new features! #RedHat #ApacheCamel...
Source: Red Hat Developer Blog
Ivo Bek
2026-06-17 07:01
🚀 Automating application migration is now possible with MigIQ! This tool transforms a Spring Boot REST API into Quarkus, showcasing a structured approach that combines graph analysis, automated planning, and parallel execution. Key phases include: 1️⃣ **Analysis**: Understanding code dependencies. 2️⃣ **Requirements**: Gathering context for the target platform. 3️⃣ **Planning**: Creating a detailed task list for migration. 4️⃣ **Execution**: Running tasks in parallel. 5️⃣ **Reporting**:...
Source: Red Hat Developer Blog
Syed M Shaaf
2026-06-17 07:01
🚀 Introducing personal AI notebooks in Red Hat Developer Hub! These notebooks serve as dedicated knowledge bases for specific projects. You can upload your project documents and interact with the AI based on that data, enhancing your workflow. Key benefits include: - Source transparency: Get evidence for every AI claim. - Data isolation: Keep queries relevant to each notebook. - Instant context: New team members can find answers quickly. Explore this feature now in developer preview! 🛠️📄...
Source: Red Hat Developer Blog
Lucas Yoon
2026-06-16 15:34
🚀 Just explored the Red Hat AI Inference on Amazon EKS! This article dives into deploying a two-GPU cluster using NVIDIA L4s, focusing on Kubernetes components like cert-manager for TLS, Istio for service mesh, and KServe for model serving. Key insights include how these elements connect and work together for efficient AI inference. 📊 Learn more about the architecture and components involved! #RedHat #Kubernetes #AIInference #AmazonEKS #CloudComputing
Source: Red Hat Developer Blog
Alexa Griffith
2026-06-16 07:01
EvalHub addresses the reproducibility crisis in AI evaluation by providing immutable records of evaluation runs. By integrating with MLflow, EvalHub captures comprehensive details about each evaluation, ensuring results are not just claims but verifiable evidence. With OCI persistence, evaluation results are stored as tamper-evident artifacts, improving compliance for regulated workloads. Learn more about building a scalable AI evaluation infrastructure! #AI #EvalHub #MachineLearning...
Source: Red Hat Developer Blog
William Caban Babilonia, Matteo Mortari
2026-06-16 07:01
Explore the latest in agentic AI and text-to-SQL! 🖥️ This installment delves into how agentic AI allows LLMs to autonomously interact with databases, improving accuracy in data queries. Unlike traditional chat interfaces, agentic systems learn and adapt, enhancing the user experience in conversational analytics. Stay tuned for more insights on orchestrating these systems! 🚀📊 #AI #DataAnalytics #TextToSQL #AgenticAI #RedHat
Source: Red Hat Developer Blog
Peter Samouelian
2026-06-15 13:12
Learn how to permanently set a network interface administratively down using NetworkManager! This article covers both legacy and new methods. Prior to NetworkManager 1.57, a special configuration file was needed. Now, with versions 1.57 and later, you can use simple nmcli commands to manage interface states without complications. For more details, check out the full article! 📡🔧 #NetworkManager #SysAdmin #Linux #Networking #nmcli
Source: Red Hat Developer Blog
Greg Scott
2026-06-15 07:16
In distributed training, gradient synchronization is a crucial phase often slowed by communication delays. This article explores how Message Passing Interface (MPI) enhances performance using collective operations like All-Reduce to synchronize gradients across GPUs efficiently. It details various parallelization methods: data, tensor, pipeline, and sharded data parallelism—each optimizing workload distribution among GPUs. Additionally, it addresses GPU-aware MPI, which reduces overhead and...
Source: Red Hat Developer Blog
Kushagra Rastogi
2026-06-15 07:16
🌟 Exploring local large language models? Check out the differences between llama.cpp and vLLM! llama.cpp is designed for efficient inference on consumer hardware, allowing users to run models with minimal GPU requirements through quantization. This approach makes LLMs more accessible to developers without dedicated hardware. On the other hand, vLLM excels in high-throughput scenarios, managing multiple requests simultaneously and optimizing GPU utilization. It's ideal for large-scale...
Source: Red Hat Developer Blog
Cedric Clyburn
2026-06-12 18:28
🚀 **Unlock Faster LLM Inference with Speculative Decoding!** Speculative decoding combines two models: a fast speculator (the hare) that predicts multiple tokens and a larger verifier (the tortoise) that validates them. This method can enhance performance by over three times for predictable tasks like code generation and structured outputs. However, it’s essential to train the speculator model on the same dataset as the verifier for optimal results. Interested in improving your LLM...
Source: Red Hat Developer Blog
Sawyer Bowerman
2026-06-12 07:00
🚀 Model-as-a-Service (MaaS) is now available with Red Hat OpenShift AI 3.4, allowing companies to run their own private AI APIs. MaaS offers a self-service path for developers, providing curated model endpoints while maintaining control over costs and security. It addresses issues like shadow AI and model deprecations by centralizing access and management. This architecture enables efficient AI integration while ensuring data sovereignty and observability. #ModelAsAService #AIIntegration...
Source: Red Hat Developer Blog
Cedric Clyburn
2026-06-12 07:00
🚀 Learn how to deploy virtual machines (VMs) in Microsoft Azure using Red Hat Satellite! This guide explains the setup process for managing both on-premises and cloud workloads seamlessly. It covers prerequisites, including Azure credentials and a Red Hat Satellite instance. Follow step-by-step instructions to create a custom VM image and configure Microsoft Azure as a compute resource within Satellite. Maximize efficiency and maintain centralized management while adapting to cloud...
Source: Red Hat Developer Blog
Øivind Ekeberg
2026-06-11 07:16
Unlock AI evaluations in your CI/CD pipeline with EvalHub's CLI! 🚀 This article details the workflow from setup to production, focusing on how to integrate automated evaluations. Key commands and environment variable configurations streamline the process, enhancing efficiency. Check out the series for more insights on building a scalable AI evaluation infrastructure! #AI #CICD #EvalHub #Automation #DevOps
Source: Red Hat Developer Blog
William Caban Babilonia, Rui Vieira, Matteo Mortari
2026-06-11 07:16
🛡️ Strengthening security in Red Hat's OpenShift AI voice agent is crucial. In a recent article, the implementation of guardrails to prevent prompt injection attacks was discussed, highlighting the importance of prompt engineering. 🔍 Key points include the use of MLflow to track conversation history and evaluating large language models for accuracy. 🛠️ Guardrails such as TrustyAI provide vital defenses against malicious inputs, ensuring reliable interactions in the voice agent. Explore more...
Source: Red Hat Developer Blog
Mike Hepburn
2026-06-11 07:00
Discover how the open-source project llm-d enhances large language model (LLM) inference on Red Hat AI. Traditional load balancers treat LLM requests as stateless, leading to inefficiencies. llm-d optimizes performance by routing requests to GPUs with relevant cached data, significantly reducing time-to-first-token by over 99% and doubling throughput. With intelligent scheduling, it adapts to real-time loads and queue depths, ensuring efficient resource use. This new approach is seamlessly...
Source: Red Hat Developer Blog
Edoardo Vacchi, Madhu Goutham Reddy Ambati