Skip to content

ENH: Automatic CUDA dependency management #62

@iwr-redmond

Description

@iwr-redmond

This feature originated in GPT4all.

You may wish to consider adding a dependency on the nvidia-cuda-runtime package for the CUDA version of xllamacpp.

Once this is done, you can integrate a modified version of the code here to automatically set the LD_LIBRARY_PATH or PATH environment variable, as appropriate, so that the runtime files are available for inference. This will hopefully allow xllamacpp to be used without needing to separately configure a CUDA runtime package.

AMD is currently building a version of ROCm that can be installed on both Windows and Linux using pip. This means that an identical feature will soon be possible for ROCm users, e.g. on Strix Halo machines.

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