fix grad thrashing of shape analysis (#40939)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/40939
Previously, when we would do shape analysis by running the op with representative inputs, we would always set the grad property to false. This led to a wrong static analysis when we would create differentiable subgraphs, and propagate shapes without also propagating requires_grad, and then uninline them.
Test Plan: Imported from OSS
Differential Revision: D22394676
Pulled By: eellison
fbshipit-source-id: 254e6e9f964b40d160befe0e125abe1b7aa2bd5e
