Artificial intelligence

A cloud service that gives data scientists and developers a powerful AI/ML

An in-depth look at a foundational GPU programming algorithm: the prefix sum. The goal is to expose the reader to the tools and language of GPU programming, rather see it only as a way to optimize certain existing subroutines.

Discover LLM Compressor, a unified library for creating accurate compressed models for cheaper and faster inference with vLLM.

Learn how to set up a cloud development environment (CDE) using Ollama, Continue, Llama3, and Starcoder2 LLMs with OpenShift Dev Spaces for faster, more efficient coding.

The first of a four-part series on introductory GPU programming, this article provides a basic overview of the GPU programming model.

This learning exercise explains the requirements for Red Hat OpenShift

Red Hat OpenShift Lightspeed, your new OpenShift virtual assistant powered by

Red Hat OpenShift AI provides tools across the full lifecycle of AI/ML experiments and models for data scientists and developers of intelligent applications.

Discover how InstructLab simplifies LLM tuning for users.

Boost your coding productivity with private and free AI code assistance using Ollama or InstructLab to run large language models locally.

Learn how to prevent large language models (LLMs) from generating toxic content during training using TrustyAI Detoxify and Hugging Face SFTTrainer.

Learn how to deploy and use the Multi-Cloud Object Gateway (MCG) from Red Hat OpenShift Data Foundation to support development and testing of applications and Artificial Intelligence (AI) models which require S3 object storage.

Train and deploy an AI model using OpenShift AI, then integrate it into an application running on OpenShift.

BERT, which stands for Bidirectional Encoder Representations from Transformers

Develop, deploy, and run large language models (LLMs) in individual server environments. The solution includes Red Hat AI Inference Server, delivering fast, cost-effective hybrid cloud inference by maximizing throughput, minimizing latency, and reducing compute costs.

This article explains how to use Red Hat OpenShift AI in the Developer Sandbox for Red Hat OpenShift to create and deploy models.

Explore large language models (LLMs) by trying out the Granite model on Podman AI Lab.

This article demonstrates how to register the SKlearn runtime as a Custom ServingRuntime, deploy the iris model on KServe with OpenDataHub, and apply authentication using Authorino to protect the model endpoints.

Develop, deploy, and run large language models (LLMs) in individual server

Explore the integration of FP8 in vLLM. Learn how to receive up to a 2x reduction in latency on NVIDIA GPUs with minimal accuracy degradation.

Explore how to use OpenVINO Model Server (OVMS) built on Intel's OpenVINO toolkit to streamline the deployment and management of deep learning models.

Event-driven Sentiment Analysis using Kafka, Knative and AI/ML

End-to-end AI-enabled applications and data pipelines across the hybrid cloud

Learn a simplified method for installing KServe, a highly scalable and standards-based model inference platform on Kubernetes for scalable AI. 

Learn how to generate complete Ansible Playbooks using natural language prompts and boost automation productivity with Red Hat's new Ansible VS Code extension.