I tried using the Relax ONNX frontend to convert an ONNX model with a QuantizeLinear layer but it failed saying this layer isn’t supported yet. I was wondering what the status of quantized ops is in Unity?
I did a bit of digging and found some discussion on this PR but I was wondering if any more thought has been put into it. Are the ops just not implemented yet like they are in Relay (QuantizeLinear) or is the holdup more so around the the debate about the necessity of a QNN dialect in Relax?
I’m new to TVM so I hope that all made sense! Thanks!