Daniel Buades Marcos

+1 for this feature too. Have you considered making a pull request with the changes in your fork, @graham00 ?

I agree that this feature would be very useful !

Agree, prebuilt CUDA 12.1 packages would be really appreciated. Like you started doing with this nightly: https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/ort-cuda-12-nightly/PyPI/ort-nightly-gpu/versions/1.17.0.dev20231205004

Thanks for the new release! However, I see that a CUDA 12 version of the python onnxruntime-gpu package wasn't included in the pypy release. I tested the CUDA 12 RC...

You are right @fvdnabee , thank you for reformulating my request.

Hello @stealthycoin, sorry for pinging you in this old PR, but you seem to be actively maintaining this repo. I was wondering if there is an underlying issue blocking the...

This would indeed be a nice feature to add. We export all our models to ONNX before deploying and this is unfortunately not currently possible with SpanMarker. Keep up the...