It’s not like neural accelerators on non-Apple consumer hardware get much use on Linux, either, so that does not sound like much of a dealbreaker.

The matrix/tensor math units added to GPUs do see widespread use, both for running LLMs and for the ML-based upscaling used by most video games these days (eg. NVIDIA DLSS). The NPUs that are separate from the GPU and designed more with efficiency in mind rather than raw performance are a different thing, and that's what's still looking for a killer app in spite of all the marketing effort.