Satyam Bhardwaj

I am experiencing the same issue in the official diffusers training example notebook [here](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb). I downloaded the notebook and ran it on my system with dual-GPU setup and set `num_processes=2`....

I am facing a similar issue when running the tutorial [volume_optimization.ipynb](https://github.com/mitsuba-renderer/mitsuba-tutorials/blob/master/inverse_rendering/volume_optimization.ipynb) on the `cuda_ad_rgb` variant. I am, however, able to reproduce the correct results with the `llvm_ad_rgb` variant originally used...

I'm surprised to see such a lack of interest from the community for a phone/tablet version of this app that works amazingly on my smart TV.