Red Hat OpenShift AI

AI model by Red Hat

Build, deploy, and scale AI models across the hybrid cloud.

A comprehensive MLOps platform for building, training, and deploying AI/ML applications across hybrid cloud environments. It provides a unified environment for data scientists to scale AI models from experimentation to production.

Model specs

The full spec card (context, pricing per token, modalities and more) on AntSpace. Sign up free to see the full spec card.

Languages
English

Category: MLOps

Fine-tuning
Supports tuning small models with enterprise-relevant data
Platform Base
Red Hat OpenShift
Deployment Options
Managed Service or Self-Managed
Cloud Availability
AWS, IBM Cloud, Google Cloud, Azure
Primary Use Case
AI/ML Lifecycle Management (MLOps)
User Access
Self-service for data scientists and developers
  • Unified platform for building, training, and deploying AI/ML apps
  • Supports 60+ models in production for enterprise customers
  • Consistent operation across hybrid cloud and edge environments
  • Optimized for high-performance partner hardware and software

Overview

Red Hat OpenShift AI is a comprehensive platform designed for data scientists and developers to build, train, and deploy AI/ML applications at scale. It provides a flexible, scalable foundation that unifies data, tools, and compute resources across hybrid cloud environments. The platform enables organizations to move AI models from experimentation to production consistently, whether on-premise, in the public cloud, or at the edge. By offering self-service capabilities, it allows large teams to manage dozens of models in production independently. Red Hat OpenShift AI is optimized for high-performance infrastructure and supports the tuning of small models with enterprise-specific data. It serves as a key component of Red Hat's broader AI portfolio, focusing on operationalizing AI for enterprise business outcomes.

Development and Deployment

  • Unified AI Lifecycle: The platform provides a unified environment for data scientists and developers to build, train, and deploy machine learning models.
  • Model Tuning: Users can tune small models with enterprise-relevant data to create specialized solutions for their business needs.
  • Resource Orchestration: The platform connects data, tools, and compute resources on a single interface to streamline the path from experimentation to production.
  • Hybrid Cloud Deployment: Organizations can deploy AI solutions consistently across hybrid cloud environments, including on-premise, public cloud, and edge locations.

Operational Efficiency

  • Self-Service Access: The platform enables self-service AI capabilities, allowing hundreds of employees to build and deploy models independently.
  • Third-Party Model Validation: Red Hat validates third-party models to ensure they run efficiently on the platform, providing flexibility in model choice.
  • Infrastructure Optimization: The platform is optimized for high-performance software and hardware infrastructure from an ecosystem of partners.
  • Enterprise Scaling: Enterprises can scale AI workloads to put dozens of models into production across various business units.

Use cases

  • Airlines use the platform to put 60+ models into production, enabling hundreds of employees to build and deploy AI independently.
  • Financial institutions unify virtual machines, containers, and AI workloads on a single platform to reduce operational costs.
  • Healthcare organizations create AI platforms that update and report patient health data to providers to improve outcomes.
  • Enterprises tune small models with their own data to develop specialized AI solutions for specific business domains.

Specifications

Sizes and variants
Compatible with validated third-party models from the Red Hat AI Ecosystem
Access
Available as a managed service on AWS, IBM Cloud, and Google Cloud, or as self-managed software on Red Hat OpenShift
Fine-tuning
Supports tuning small models with enterprise-relevant data
Platform Base
Red Hat OpenShift
Deployment Options
Managed Service or Self-Managed
Cloud Availability
AWS, IBM Cloud, Google Cloud, Azure
Primary Use Case
AI/ML Lifecycle Management (MLOps)
User Access
Self-service for data scientists and developers
Model Support
Validated third-party and custom models

How it works

  1. Deployment Choice: Organizations choose between managed services on major cloud providers or self-managed deployment on their own OpenShift clusters.
  2. Model Development: Data scientists use the unified platform to connect data sources, select tools, and access compute resources.
  3. Training and Tuning Tune: Teams build, tune, and train models using enterprise data within the secure environment.
  4. Production Scaling: Validated models are moved into production across hybrid cloud footprints, from datacenters to the edge.

FAQ

What is Red Hat OpenShift AI?

Red Hat OpenShift AI is a comprehensive platform that provides data scientists and developers with a powerful environment for building, training, and deploying AI/ML applications.

How does it help with self-service AI?

The platform connects data, tools, and compute resources on one platform, allowing employees to build and deploy AI on their own.

Can I use third-party models with this platform?

Yes, Red Hat validates that third-party models run on its AI platforms and may optimize them for more efficient use.

Where can I deploy Red Hat OpenShift AI?

It operates consistently across hybrid cloud environments, including the core datacenter, public clouds, and the network edge.

Added by AntSpace from public sources (redhat.com).

Related

More AI models by Red Hat