David MacLeod

Thanks, will check it out

Do you know how close it is to being merged? (just trying to gauge whether I should wait - or working from the branch)

@gaxler what is the relationship between this branch and `aot.py` on master? Will they both continue to exist after this branch is complete?

I was also wondering this, I believe ONNX supports sequence type inputs so this should be possible. It seems that this is possible in PyTorch when tracing, but not when...

@BowenBao are there any plans to support `Dict[str, Tensor]` as input?

@tridao I could take a look at implementing this as also keen for T4 support, any obvious caveats that spring to mind?