[Feature Request] Provide a C++ API

[tranlm]

🚀 Feature

I'm wondering if you plan on providing a C++ (or C#) API.

Motivation

Many programs that operate on device use C++ or C#. This would enable us developers to adopt it for use.

Alternatives

I've been using llama.cpp, openvino, or onnx runtime genai.

Additional context

NA