[Request] Support voxelnext to onnx conversion

[Mysterium-sch]

I am looking to convert the voxelnext model to onnx and I am finding it difficult to find instructions on how to do so. I think this would be a useful addition as voxelnext is a commonly used lidar model.

[Mysterium-sch]

I have been working on using the code implemented for bevfusion for implementing voxelnext. I am successfully able to export the voxelnext model but I run into problems when trying to run inference. I think the problem is because the voxelnext forward method contains:

x_conv5.indices[:, 1:] *= 2
x_conv6.indices[:, 1:] *= 4
x_conv4 = x_conv4.replace_feature(torch.cat([x_conv4.features, x_conv5.features, x_conv6.features]))
x_conv4.indices = torch.cat([x_conv4.indices, x_conv5.indices, x_conv6.indices])
        
out = self.bev_out(x_conv4)

I think when the c++ code attempts to build the model it is missing these operations, are there any suggestions on how I can add these operations so they are built with the rest of the model