Skip to content

Cuda version #117

Description

@jiaji-huang

Is this package tested on more recent cuda and pytorch versions?

My code calls fast_transformers.causal_product, which is actually the only function I call from this package.

I setup this package with latest pytorch 1.13.0+cuda11.6, and get NaN errors at training. This, however, doesn't happen with the older pytorch 1.7.1+cuda11.0.

Activity

  1. jiaji-huang commented on Dec 8, 2022

    @jiaji-huang
    Author

    Actually, a follow-up of my question, I think the issue can be resolved by installing from source.

    Instead of pip install pytorch-fast-transformers, cloning the repo and running python setup.py install gets rid of the NaN I had before.

    But I'd like to hear more thoughts.

  2. yanshengran-github commented on Dec 11, 2024

    @yanshengran-github

    Actually, a follow-up of my question, I think the issue can be resolved by installing from source.

    Instead of pip install pytorch-fast-transformers, cloning the repo and running python setup.py install gets rid of the NaN I had before.

    But I'd like to hear more thoughts.

    I followed your instructions ( pytorch1.7.1 + cuda11.0 & install from source ) but still have the NaN error.
    It seems the function in 'causal_product_cuda.cu' cannot be imported.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

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