Skip to content

Configure self-hosted CI runner capable of performing inference for tests #82

@mattt

Description

@mattt

Related to #72

GitHub-hosted runners can't feasibly load or execute models required for MLX, Ollama, and CoreML tests 1.

Instead, we can set up a self-hosted runner that's up to the task.

Footnotes

  1. GitHub does offer larger runners, but they come with caveats for macOS.

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions