Red Hat AI

PowerUP 2025 is the week of May 19th. It's held in Anaheim, California this year

Learn how to use pipelines in OpenShift AI to automate the full AI/ML lifecycle on a single-node OpenShift instance.

Jupyter Notebook works with OpenShift AI to interactively classify images. In

LLM Compressor bridges the gap between model training and efficient deployment via quantization and sparsity, enabling cost-effective, low-latency inference.

Accelerate the development and deployment of enterprise AI solutions across the

Learn how the dynamic accelerator slicer operator improves GPU resource management in OpenShift by dynamically adjusting allocation based on workload needs.

This tutorial shows you how to use the Llama Stack API to implement retrieval-augmented generation for an AI application built with Node.js.

Learn about the Red Hat OpenShift AI model fine-tuning stack and how to run performance and scale validation.

Learn how NVIDIA GPUDirect RDMA over Ethernet enhances distributed model training performance and reduces communication bottlenecks in Red Hat OpenShift AI.

Learn how the DeepSeek training process used reinforcement learning algorithms to generate human-like text and improve overall performance.

Explore performance and usability improvements in vLLM 0.8.1 on OpenShift, including crucial architectural overhauls and multimodal inference optimizations.

Discover a new combinatorial approach to decoding AI’s hidden logic, exploring how neural networks truly compute and reason."

Discover how to fine-tune large language models (LLMs) with Kubeflow Training, PyTorch FSDP, and Hugging Face SFTTrainer in OpenShift AI.

Explore how Red Hat Developer Hub and OpenShift AI work together with OpenShift to build workbenches and accelerate AI/ML development.

This article demystifies AI/ML models by explaining how they transform raw data into actionable business insights.

Learn how to build AI applications with OpenShift AI by integrating workbenches in Red Hat Developer Hub for training models (part 1 of 2).

Discover the new Llama 4 Scout and Llama 4 Maverick models from Meta, with mixture of experts architecture, early fusion multimodality, and Day 0 model support.

Discover Async-GRPO, a new library for reinforcement learning tasks that efficiently handles large models, eliminates bottlenecks, and accelerates experiments.

Discover how the adaptive SVD approach enables LLMs to continually learn and adapt without forgetting previously acquired knowledge.

Explore how RamaLama makes it easier to share data with AI models using retrieval-augmented generation (RAG), a technique for enhancing large language models.

Learning the naming conventions of large language models (LLMs) helps users select the right model for their needs.

Explore how to run tools with Node.js using Llama Stack's completions API, agent API, and support for in-line tools, local MCP tools, and remote MCP tools.

Learn how quantized vision-language models enable faster inference, lower costs, and scalable AI deployment without compromising capability.

Sign up for the Red Hat Developer Newsletter

Headed to DevNexus 2025? Visit the Red Hat Developer booth on-site to speak to our expert technologists.