Skip to content

Better handling for configurations that WebLLM doesn't work on. #4

@erikh2000

Description

@erikh2000

There are some devices where WebLLM starts loading and never finishes, sometimes due to lack of video ram.

Example - my Fairphone will load the model to persistent storage, and then stop at 4gb loading it into GPU.

Can I do something to detect this in advance and stop / advise against the load?

Can I recover from a failed load?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions