pytorch

e2c1533c - [quant][core][gpu][eager] Improved quantized conv operator in cudnn (#72770)

[quant][core][gpu][eager] Improved quantized conv operator in cudnn (#72770) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/72770 This PR improves upon PR70622 by removing the call to_make_per_tensor_quantized_tensor and directly creating a quantized int8 tensor that is passed into raw_cudnn_convolution_forward as opposed to a non-quantized int8 tensor. Test Plan: Imported from OSS Reviewed By: H-Huang Differential Revision: D34243926 Pulled By: dzdang fbshipit-source-id: 7725db27d0a276e8108086fecb7ecb18aa227102 (cherry picked from commit e20e99c7b979c0db60562a744a546592a20befa0)