Machine learning models are forced to use single thread

[AIApprentice101]

Thank you for the great tool. I have an issue when implementing RQ in my project, where I use a Transformer model (Pytorch backend). Without RQ, the model is using multiple threads of the CPU. But when I spin up the model in RQ's SimpleWorker, the model is forced to use just one thread; causing it to be super slow.

Any help would be much appreciated.