Optional GPU support with Triton

[Mec-iS]

I'm submitting a

• [x] feature request.

Current Behaviour:

OpenAI Triton looks like a user-friendly language for GPU kernel programming: https://github.com/openai/triton It is written in C and it would be great to have Rust bindings for it, so to allow Smartcore to provide optional GPU support for matrix operations. Viability should be researched, see this issue

Expected Behaviour:

Matrix operations using Triton in presence of GPU