News for hackers. Stuff that matters.
Re:PyTorch 2.0 Release by sebzim4500 on Wednesday March 15, 2023 @05:20PM (#35174881)
Based on George Hotz's testing it is very broken. It's possible it has improved since then, I guess but he streamed this a few weeks ago.
Re:PyTorch 2.0 Release by danieldk on Wednesday March 15, 2023 @05:41PM (#35175123)
We tested inference for all spaCy transformer models and they work:

https://explosion.ai/blog/metal-performance-shaders

It depends very much on the ops that your model is using.

Re:PyTorch 2.0 Release by dagmx on Wednesday March 15, 2023 @05:27PM (#35174964)
It supports a subset of the operators (as mentioned in the release notes). I don’t think it’s broken for the ones that it does support though.
Re:PyTorch 2.0 Release by norgie on Wednesday March 15, 2023 @05:38PM (#35175081)
Yes, this is my experience. Many off the shelf models still don't work, but several of my own models work great as long as they don't use unsupported operators.
Re:PyTorch 2.0 Release by glial on Wednesday March 15, 2023 @05:57PM (#35175299)
Where can I find a list of the supported operators?
Re:PyTorch 2.0 Release by PaulMest on Thursday March 16, 2023 @02:35AM (#35178868)
This is the master tracking list for MPS operator support: https://github.com/pytorch/pytorch/issues/77764
Re:PyTorch 2.0 Release by mochomocha on Wednesday March 15, 2023 @05:56PM (#35175279)
That's been my experience. However when fallback to CPU happens, it sometimes end up making a specific graph execution slower. But that's explicitly mentioned by the warning and pretty much expected.
Re:PyTorch 2.0 Release by brucethemoose2 on Wednesday March 15, 2023 @05:59PM (#35175317)
You'd think it would fall back to GPU/CPU for unsupported operations instead of failing, but I guess thats easier said than done.
Re:PyTorch 2.0 Release by rfw300 on Wednesday March 15, 2023 @09:11PM (#35176918)
In fact there is an environment variable that enables exactly that. There are obviously performance issues associated with that, but it does work.
Re:PyTorch 2.0 Release by bigbillheck on Wednesday March 15, 2023 @05:39PM (#35175099)
Based on George Hotz's performance at twitter I wouldn't bet he wasn't holding it wrong.
Re:PyTorch 2.0 Release by jeron on Wednesday March 15, 2023 @06:40PM (#35175700)
so, you would bet he was holding it wrong?
Re:PyTorch 2.0 Release by remexre on Thursday March 16, 2023 @12:14AM (#35178065)
More likely, no bet would be placed.
Re:PyTorch 2.0 Release by laichzeit0 on Thursday March 16, 2023 @07:47AM (#35180724)
I could fine-tune a Detectron2 model a few months ago using PyTorch and MPS backend [1]. I'd be interested if it's working yet.

https://github.com/facebookresearch/detectron2/issues/4342