pytorch

57529d48 - [quant] Fix applying non-zero offset 1 to null pointer in quantized interpolation (#65570)

[quant] Fix applying non-zero offset 1 to null pointer in quantized interpolation (#65570) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/65570 Although this is not an issue that could pop-up in practice, LLVM-12 throws an error about this issue if not checked. Test Plan: `buck test mode/dev //caffe2/test:quantization -- --exact 'caffe2/test:quantization - test_empty_batch (quantization.core.test_quantized_op.TestQuantizedOps)'` Reviewed By: r-barnes Differential Revision: D31151681 fbshipit-source-id: e039c6aa1687a61ef6774f045744dc9d768d5c80