Skip to content

Running LM in half precision #5

@timt51

Description

@timt51

Thank you for releasing MiniFold!

I noticed that running the LM in half precision is currently disabled:

# For some reason having inference issues with autocast on the LM

Can you say more about what the inference issues are with autocast on the LM?

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