Intel puts a huge priority on DL framework support before releasing related hardware, going back to at least 2017.

I assume that hasn't changed.

OpenVino is entirely open-source and can run PyTorch and ONNX models, so this is definitely not a topic of concern. PyTorch also has native Intel GPU support https://docs.pytorch.org/docs/stable/notes/get_start_xpu.htm...

There is PyTorch support on oneAPI.