Getting Cuda runtime error when running the get started code snippet.

#19

by tommerraz - opened Jun 28, 2023

Jun 28, 2023

I am trying to test out the model on an nvidia dgx1 server and I get the error:
RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling cublasGemmStridedBatchedExFix

I get this error while running the getting started code snippet with pipeline from the readme.

Here are some veriosning:
Python 3.8.10
cuda version: 11.6
pytorch: 1.13.0

when running torch.cuda.is_available() it returns True

Please message if you need more information
And will appreciate the help

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment