Damian Szwichtenberg

@rusty1s I have had a minimal implementation of `[segment | grouped]_matmul` ready for some time. Was working on optimization, but in such a case I'll create a PR with basic...

@kgajdamo @JakubPietrakIntel Could you please take a look at this issue?

`(segment|grouped)_matmul` had an incomplete dispatch types set, I've fixed CPU implementation with [pyg-lib @ 272](https://github.com/pyg-team/pyg-lib/pull/272) (@puririshi98 could you please take a look at CUDA implementation?). If you find any custom...

I will take care of [segment_matmul](https://pyg-lib.readthedocs.io/en/latest/modules/ops.html#pyg_lib.ops.segment_matmul) forward implementation for CPU. 😉