v4.5.0 is not compatible with `torch>=2.*.*+cu121`

Hello
the last release works great with versions of pytorch that use python cuda packages, but when torch that is precompiled with cuda binaries is installed, this error appears:

Unable to load any of {libcudnn_cnn.so.9.1.0, libcudnn_cnn.so.9.1, libcudnn_cnn.so.9, libcudnn_cnn.so}
Invalid handle. Cannot load symbol cudnnCreateConvolutionDescriptor

the only solution so far is to downgrade to 4.4.0 although CuDNN v9.1 is installed both using pip and bundled with pytorch
https://github.com/jhj0517/Whisper-WebUI/pull/348

Update:
as per @BBC-Esq research, ctranslate2>=4.5.0 uses CuDNN v9 which requires CUDA >= 12.3.
Since most issues occur from a conflicting torch and ctranslate2 installations these are tested working combinations:

For google colab users, the quick solution is to downgrade to 4.4.0 as of 24/10/2024 as colab uses torch==2.5.0+cu12.1

No source file, test, or entry point is named. Start by reproducing the reported error across the listed torch and CTranslate2 version combinations, then inspect how the release handles CUDA and cuDNN compatibility. Done means the supported combinations are either compatible in v4.5.0 or the limitation is clearly documented.