[ONNX] Quantization documentation outdated

[anuragsingh-tt]

The documentation here states the following:

Quantization parameters are carried out of line in the ONNX protobuf
and will be repatriated upon import to torch. The exact mechanism is
not yet implemented.

This is outdated. The following simple conv2d in onnx:

contains the quantization parameters in line. There are already test cases in the torch-mlir repo (e.g. here) that can translate this successfully to torch.