Tim Dettmers

One change is good, the other would be a degradation in speed. Lets discuss how to fix this while maintaining speed for other GPUs.

The problem is that LeNet-5 has a bottleneck with very few connections and if you get by chance a configuration where no connection between one and the other layer exists...

In theory yes, but not with this library. See #1 for a discussion on using sparse computation in this library and in PyTorch in general.

The convergence rate is approximately the same for sparse and dense networks. What I saw is that the networks react a bit differently to certain learning rates. You can run...

I have to check this more carefully when I have more time. Thank you for your contribution! Sorry for taking so long to look at this.

Yes, it should work without any problem. You can just follow the steps of wrapping the transformer into the `Masking` class and it should work just fine. What is happening...

Thank you so much for this contribution. We discussed internally how to best integrate this and other libraries. We think it is best to abstract the `extern C` interface so...

Just to give you a heads-up about timeline and logistics on this issue: I am interviewing for academic positions in the next two months and will only be sparingly able...

Thank you. On second thought, I think your idea of a slightly higher-level device abstraction is better than what we had in mind before. We could lift the interface by...

The main error that you posted (about LD_LIBRARY_PATH) has been fixed, but the main issue here is Apple Silicon support. I currently have no plans of implementing this, but I...