Skip to content

OneLLM #7596

@dcarracedo

Description

@dcarracedo

Description
Create a new component called OneLLM for LLM inference, composed of:

  • GUI tab integrated into OpenNebula Sunstone
  • REST API for backend logic
  • Hugging Face Hub driver to sync/download models into OpenNebula datastores

Use case

  • Administrators
    • Define reusable Instance Types in a dedicated UI.
    • Configure and run model pre-download from Hugging Face.
  • End users
    • Browse pre-downloaded models only
    • Deploy by choosing model + instance type

Interface Changes
CLI and GUI

Additional Context
Please feel free to add any other context or screenshots about the feature request here. Or any other alternative you have considered to address this new feature.

Progress Status

  • Code committed
  • Testing - QA
  • Documentation (Release notes - resolved issues, compatibility, known issues)

Metadata

Metadata

Assignees

No one assigned

    Projects

    No projects

    Milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions