Getting Cuda runtime error when running the get started code snippet.
#19
by
tommerraz
- opened
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