Support quantize_ for convolution on XNNPACK

[GregoryComer]

XNNPACK's partitioner and lowering logic doesn't recognize the quantize_ (de)quantize_affine representation in the IR for convolution nodes. We need to wire this up.

Example quantization code:

conv_config = IntxWeightOnlyConfig(
        weight_dtype=torch.int8,
        granularity=PerAxis(0),
    )
    quantize_(
        model,
        conv_config,
        lambda m, fqn: isinstance(m, torch.nn.Conv2d),
    ) 

cc @digantdesai @cbilgin