Torch.onnx customized op inputs unexpected

[jinfagang (Jin Tian)]

I have a customized op like this:

class AtomFakeQuantizeLearnablePertensorAffine(torch.autograd.Function):
    @staticmethod
    def forward(ctx, x, scale, zero_point, quant_min, quant_max, grad_factor):
        return torch._fake_quantize_learnable_per_tensor_affine(
            x, scale, zero_point, quant_min, quant_max, grad_factor
        )

    @staticmethod
    def symbolic(g, x, scale, zero_point, quant_min, quant_max, grad_factor):
        logger.debug("symbolic for: AtomFakeQuantizeLearnablePertensorAffine")
        return g.op(
            "::AtomFakeQuantizeLearnablePertensorAffine",
            x,
            scale,
            zero_point,
            quant_min_i=quant_min,
            quant_max_i=quant_max,
        )

this defined inputs to be 5, but the exported onnx model make quant_min and quant_max as attributes.

this is unexpected, how to avoid it?