Skip to content

[Feature Request] Publish LLaVA-NeXT to PyPI for easier integration #503

@songyuc

Description

@songyuc

Hi LLaVA-NeXT team,

I recently encountered issues when using lmms-eval where manual cloning and installation of this repository was required.

It would be extremely helpful if LLaVA-NeXT could be published to PyPI (e.g., as pip install llava-next). This would allow downstream projects (like lmms-eval) to list it as a dependency, automating the installation process and ensuring version reproducibility.

Even if the import name remains llava, having a distributable package on PyPI would significantly improve the developer experience.

Thank you for your great work!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions