Matthew Douglas

@Titus-von-Koeller Yes, the failures were related to some tolerances and the stochastic nature of some of the tests. I get similar results on my Linux machine. I do think the...

Rebased

> > Rebased > > This is really weird, somehow the diff of the PR got all messed up now. This makes it really hard to review. > > It...

I think I understand the change in `forward()` but I'm struggling to understand what I see in `backward()`. The change in forward is at least limited in surface area to...

What OS are you running on? `bitsandbytes` v0.43.0 wheels requires glibc 2.24, and it seems like you might be closer to ~2.17. It's interesting that pip installed the wheel when...

@a-turcu It's important to note that [CentOS 7 will reach EOL in about 100 days](https://www.redhat.com/en/topics/linux/centos-linux-eol). It should be possible to compile for a system that old. You don't have to...

I'm also interested in helping where I can. I don't have a Mac machine, but I would like to have native builds for Windows. I'm also interested in aarch64 for...

@eusip I'm on the Huggingface Discord, where my username is `TheUltraInstinct`.

@abhilash1910 I have a few questions. 1. What would be the advantage of using the PTX (Nvidia) target on the SYCL implementation vs. existing CUDA backend? I can understand the...

@abhilash1910 That sounds reasonable to me and should result in more iterative, digestible PRs until it's ready for prime time.