Justin Chu

Thanks - is the ops in `torch.ops.quantized_decomposed` still used, or is `torch.ops.quant` new/different? Do we need to import torchao to register these ops or are they native to pytorch?

Could you point me to where the torch.ops.quant.* ops are declared, and is there a list of all ops available?

> is there any progress with this operator？ I haven’t had time to fill in the details. Any help appreciated

We think we can get away with it in torch using some adapters after discussion

We are working on a solution in https://github.com/microsoft/onnxscript/issues/693. I expect the support will come this Fall.

Complex support implemented as operations on real views of complex tensors.

Not yet for onnx. We are building more of them into torch.onnx.dynamo_export

> What do you think on possibility of backporting of export complex-dtype ops onto the older onnx symbolic/torch.onnx.export machinery? This is possible, but is not going to be priority. Contribution...

> Regarding TorchScript -> FX graph conversion, there seems a newly merged: Nice, thanks - it looks promising. We will be supporting this route when the PRs are in.

I think there is a renewed interest for this proposal @onnx/sig-operators