Check that torch SVD returns eigenvalues in sort order

[charlesmartin14]

Accordiong to ChatGPT

As of my knowledge cutoff in September 2021, PyTorch's SVD implementation had some limitations. It uses a batched SVD routine, which can cause problems with larger matrices due to GPU memory limitations. PyTorch's SVD also may return singular values that are not sorted, which is non-standard behavior that can surprise users.

[charlesmartin14]

also

On the other hand, CuPy uses a more standard, non-batched routine for SVD, which is less likely to run into memory issues for large matrices. Also, CuPy's SVD returns singular values in descending order, which is the typical behavior expected by users.