[Quantization] How to quantize nn.bias_add?

Development
#1

Is there a setting to enable quantization of nn.bias_add? I have int8 bias I want to broadcast add to int8 output of nn.conv2d and nn.dense.

#2

More generally, are there any resources on how to implement quantize for relay ops as in the source?

@vinx13 @masahi @ziheng

#3

Not sure, I think you need one of those registration like the one below for bias_add.

RELAY_REGISTER_OP("nn.dense")
.set_attr<FForwardRewrite>("FQRealizeRewrite", DenseRealize);

Our quantization support is in a rough state at the moment :slight_smile: (no doc, just code)