pytorch

84975339 - [PyTorch] AOTI: generate reused thread_locals when tensors provably have static shape (#110892)

[PyTorch] AOTI: generate reused thread_locals when tensors provably have static shape (#110892) If a Tensor can be reused and has static shape, we can just cache it across iterations. This is meant as a quickly shippable overhead reduction for CPU overhead-bound use cases that we can ship without relying on memory planning. Differential Revision: [D50023678](https://our.internmc.facebook.com/intern/diff/D50023678/) Pull Request resolved: https://github.com/pytorch/pytorch/pull/110892 Approved by: https://github.com/bertmaher ghstack dependencies: #110876, #110877, #110909