Support microsoft contrib ONNX operator MatMulNBits

[hgaspar]

Such an operator appears in LLM models quantized to int4 (also with GroupQueryAttention nodes), via the genai tool.

Only N=4 needs to be supported in near term (i.e. 4 bits)

For reference, see the operator description in:

https://github.com/microsoft/onnxruntime/blob/main/docs/ContribOperators.md#com.microsoft.MatMulNBits

Here, supports means:

1. Ability to parse models that contain it.
2. Implement it via known operators.