Feature Overview

Enable support for RHOAI on Red Hat OpenStack, allowing organisations to deploy, manage, and run RHOI workloads within their private cloud infrastructure powered by Red Hat OpenStack. This feature extends the deployment options for RHOI beyond bare-metal, providing greater flexibility and control over AI workloads in on-premises environments.

Goals 

Primary User Personas:

• Administrator persona: Gain the ability to deploy and manage RHOAI in their Red Hat OpenStack environments with familiar tools.
• MLOps and App Developers persona: Access RHOIAI capabilities within the organization's private cloud, facilitating collaboration and innovation.
• As a OSP cloud user I want to try LLM on RHOAI in a virtual machine deployed on my OSP18 cloud.
• As a OSP cloud user I want to utilize the full potential of RHOAI to avoid Bare Metal allocation to RHOAI outside of my OSP18 cloud.

Value:

• Expanded deployment options: Users can now deploy RHOAI on RHOSO, leveraging existing private cloud investments.
• Data sovereignty and compliance: Organizations can keep sensitive data on-premises, meeting regulatory and compliance requirements.
• Integrated management: IT operations teams can manage RHOAI instances alongside other workloads within RHOSP/RHOSO, streamlining operations.
• Optimized resource utilization: Efficient use of hardware resources, including NVIDIA GPU acceleration, within the RHOSP/RHOSO environment.

Requirements

• Compatibility:
  RHOAI must be fully compatible with Red Hat OpenStack Services on OpenShift 18.0. It should support essential Red Hat OpenStack services required for deployment.

• Hardware Acceleration:
  Ensure support for GPU passthrough in Red Hat Red Hat OpenStack. Compatibility with NVIDIA only for this Feature.

• Documentation:
  Provide comprehensive installation guides tailored for the administrator persona. 

Non-Functional Requirements:

• Performance:
  Provide performance benchmarks for RHOAI on Red Hat OpenStack.

• Scalability:
  Support scaling out by launching RHOAI instances for inferencing with Octavia load balancing vLLM

Checklist:

• OpenStack Services on OpenShift 18.0
• Ensure GPU passthrough support is functional.
• Update RHOAI and Red Hat OpenStack documentation with new deployment guides.
• Conduct security assessments and address any vulnerabilities.
• Perform performance benchmarking and optimisation.
• Train support and field teams on the new feature.
• Release notes and customer communication prepared.

Documentation

New Install section for Red Hat OpenStack
New requirements section