[mindcrime]

Mesa advertises support for OpenCL[1], so the idea of using it as an ML backend isn't ridiculous. But I can't speak to whether or not anybody has actually tried to make that work, or where it stands.

[1]: https://www.khronos.org/opencl/

[synergy20]

I think OpenCL lost the battle in ML era, CUDA crashed it, followed by newcomers like SYCL and ROCm these days.

[mindcrime]

Oh yeah. I didn't mean to suggest this as something anybody would want to do for any kind of serious use. Just pointing out that, in the abstract, the idea of doing it isn't totally ridiculous.