Tim Dettmers

Happy new year :)

Thank you for all the work on this PR @younesbelkada, @sgugger, @michaelbenayoun! Regarding the `transformers` vs `optimum` question: From my understanding of the libraries, I think if people want to...

I will look into this and double buffering after I have taken a closer look at the codebase and the PyCUDA API. Double buffering is a bit more complicated, because...

We can already generate those with sphinx and we could host them on https://readthedocs.org/. There is probably also github integration for that.

Can you please provide the output of `python -m bitsandbytes`. It seems that your CUDA driver is not detected, and as such, no GPU is visible to the bnb cuda...

Hi Mitchell! Currently, this is expected, but we are aware of the issues, and we plan to solve the issues that can be resolved in future releases. To summarize the...

I would have expected to be faster for GPT-J. But that is great feedback, and this then will be one of my cornerstone models for benchmarking. Thank you, Mitchell!

We analyzed the use case and found issues that we could partially resolve, speeding up smaller models by 2x. Please give the newest release, 0.32.0, another try. You should still...

Thank you, Mitchell! The new performance data looks good and will help us to calibrate. We will keep you updated as we make progress. We are currently planning to support...

This is a great addition, thank you! One issue with the conda install is that only a limited number of CUDA versions are supported. We also offer a script to...