pytorch

d9aa0b53 - [PyTorch] Migrate TI usage in ATen/native/quantized to borrowing (#58307)

[PyTorch] Migrate TI usage in ATen/native/quantized to borrowing (#58307) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/58307 Borrowing is more efficient, and we can see in all these cases that the TensorIterator doesn't outlive the input & output Tensors. ghstack-source-id: 129598791 Test Plan: Existing CI Reviewed By: ezyang Differential Revision: D28445922 fbshipit-source-id: ce12743980296bab72a0cb83a8baff0bb6d80091