Autodiff is a place where there is a gulf between Julia and Python, one
that I think can't be bridged well: JuliaDiff is astonishingly flexible and performant.
Also python is still doing great with Jax and PyTorch.
I don't know much about Jax. I've seen competent benchmarks showing an order of magnitude benefit for using ReverseDiff from the AutoDiff suite over Autograd, which is what Pytorch uses for reverse-mode autodiff
It really should be updated to have basically the content of this thread https://discourse.julialang.org/t/state-of-automatic-differe...