The project delivers a comprehensive full-stack solution for the Intel® Enterprise AI Foundation on the OpenShift platform, applicable across data center, cloud, and edge environments. It utilizes innovative General Operators technology to provision AI accelerators, including the Intel Gaudi Processor, Flex and Max GPUs, and Xeon CPU accelerators such as QAT, SGX, and DSA. Additionally, the project introduces solutions for integrating Gaudi Software or OneAPI-based AI software into OpenShift AI. Key AI workload integrations, such as LLM inferencing, fine-tuning, and post-training for enterprise AI, are under development. The plans also include the GPU network provisioning and full-stack integration with OpenShift.
See reference BIOS Configuration required for each feature.
Use one of these two options to provision an RHOCP cluster:
- Use the methods introduced in RHOCP documentation.
- Use Distributed CI as we do in this project.
In this project, we provisioned RHOCP 4.16 on a bare-metal multi-node cluster. For details about the supported RHOCP infrastructure, see the Supported Platforms page.
If you are familiar with the steps mentioned below to provision the accelerators, you can use One-Click solution as a reference to provision the accelerator automatically.
Follow Setting up HabanaAI Operator to provision Intel Gaudi AI accelerator.
Please follow the steps below to provision the hardware features
- Setting up Node Feature Discovery
- Setting up Machine Configuration
- Setting up Out of Tree Drivers
- Setting up Device Plugins
You can use the instructions in the link to verify the hardware features provisioning.
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
Here are the reference workloads built on the end-to-end solution and Intel hardware feature provisioning in this project.
This section discusses architecture and other technical details that go beyond getting started.
Check the link for the Release Notes.
If users encounter any issues or have questions regarding Intel Technology Enabling for OpenShift, we recommend them to seek support through the following channels:
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.
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.
See CONTRIBUTING for more information.
To report a potential security vulnerability, please refer to security.md file.
Distributed under the open source license. See LICENSE for more information.
Intel has adopted the Contributor Covenant as the Code of Conduct for all of its open source projects. See CODE_OF_CONDUCT file.