Skip to content

Is sequence cpu offload available? #54

@Willian7004

Description

@Willian7004

I noticed that you only use model offload in the code. Can it runs on 8g or less vram with sequence offload?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions