I’ve also found that some versions of torch get quite different inference result...

		gcr 3 months ago \| parent \| context \| favorite \| on: A bug that taught me more about PyTorch than years... I’ve also found that some versions of torch get quite different inference results on MPS, ignoring gradient. See https://gist.github.com/gcr/4d8833bb63a85fc8ef1fd77de6622770