Hi,
Sorry for the inaccurate answer on the previous post.
After some more digging, you are absolutely right that this is supported in theory.
The reason why we disable it is because while doing experiments, we observed that these GPUs are not very powerful for most users and most are better off using the CPU part which will actually be faster.
And so while most users do have these processors, most of them should not use them for ML workloads.
If you want to try this on your machine, you should be able to re-enable it relatively easily when building from source by simply making this if statement true: pytorch/MPSDevice.mm at 8571007017b61d793c406142bad6baeda331d00d · pytorch/pytorch · GitHub
Since we support only one device, you might want to make sure this does not shadow a more powerful AMD GPU (if you have two GPUs on that machine).
I think the plan is to keep this disabled for now and only enable it if there is strong signal that people need this.
Curious to hear if that works for you!