Intel® Technology Enabling for OpenShift*

Overview

The Intel Technology Enabling for OpenShift project provides Intel Data Center hardware feature-provisioning technologies with the Red Hat OpenShift Container Platform (RHOCP). The technology to deploy and manage the End-to-End (E2E) solutions as well as the related reference workloads for these features are also included in the project.

These Intel Data Center hardware features currently include:

  • Intel® Software Guard Extensions (Intel® SGX)
  • Intel® Data Center GPU Flex Series
  • Intel® QuickAssist Technology (Intel® QAT)

The following features will be included in future releases.

  • Intel® Data Center GPU Max Series
  • Intel® Data Streaming Accelerator (Intel® DSA)
  • Intel® In-Memory Analytics Accelerator (Intel® IAA)
  • Intel® FPGA N6000

See details about Supported Intel Hardware features and Supported RHOCP Versions.

For detailed information about releases, please refer Release Information.

Figure-1 is the Architecture and Working Scope of the project

Alt text

Figure-1 Intel Technology Enabling for OpenShift Architecture

Supported platforms

This section describes the RHOCP infrastructure and Intel hardware features supported by this project. The project lifecycle and support channels can also be found here.

Getting started

See reference BIOS Configuration required for each feature.

Provisioning RHOCP cluster

Use one of these two options to provision an RHOCP cluster:

In this project, we provisioned RHOCP 4.14 on a bare-metal multi-node cluster. For details about the supported RHOCP infrastructure, see the Supported Platforms page.

Provisioning Intel hardware features on RHOCP

Please follow the steps below to provision the hardware features

  1. Setting up Node Feature Discovery
  2. Setting up Machine Configuration
  3. Setting up Out of Tree Drivers
  4. Setting up Device Plugins

Verifying hardware feature provisioning

You can use the instructions in the link to verify the hardware features provisioning.

Upgrade (To be added)

Reference end-to-end solution

The reference end-to-end solution is based on Intel hardware feature provisioning provided by this project.

Intel AI Inferencing Solution with OpenVINO and RHOAI

Reference workloads

Here are some reference workloads built on the end-to-end solution and Intel hardware feature provisioning in this project.

  • Large Language Model (To be added)
  • Open Federated Learning (To be added)

Advanced Guide

This section discusses architecture and other technical details that go beyond getting started.

Release Notes

Check the link for the Release Notes.

Support

If users encounter any issues or have questions regarding Intel Technology Enabling for OpenShift, we recommend them to seek support through the following channels:

Commercial support from Red Hat

This project relies on features developed and released with the latest RHOCP release. Commercial RHOCP release support is outlined in the Red Hat OpenShift Container Platform Life Cycle Policy and Intel collaborates with Red Hat to address specific requirements from our users.

Open-Source Community Support

Intel Technology Enabling for OpenShift is run as an open-source project on GitHub. Project GitHub issues can be used as the primary support interface for users to submit feature requests and report issues to the community when using Intel technology provided by this project. Please provide detailed information about your issue and steps to reproduce it, if possible.

Contribute

See CONTRIBUTING for more information.

Security

To report a potential security vulnerability, please refer to security.md file.

License

Distributed under the open source license. See LICENSE for more information.

Code of Conduct

Intel has adopted the Contributor Covenant as the Code of Conduct for all of its open source projects. See CODE_OF_CONDUCT file.