GitLab

Enable simplify qdq to work with FP8 types, add warning for fp8 when loading mxr

Updated onnx.proto files to be same as onnx==1.14.1 that is used by MIGraphX.   Added more switch cases in onnx parser to handle FP8 dtypes.

Ref Unique Operator only

Add min and max reduction modes
Implement duplicate index handling
Add corresponding reference, onnx, and verify tests.

Simplify what we parse the ONNX operator ConstantOfShape into a literal for a static shape