Skip to content

Inference requirements #13

@martinbchnr

Description

@martinbchnr

Hi,

first of all, congrats and thanks for open-sourcing your work!

I tried running anycam on a local 80GB A100 without success as I encounter CUDA OOMs. Is there another set of weights or paradigm to follow to make this work?

Kind regards :)

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