[Quant][core][gpu] Implemented support for relu in quantized conv operator using cudnn (#73337)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73337
This PR extends the conv cudnn operator to include relu. The support is implemented using optional variables.
This PR extends the conv cudnn operator to include relu. The support is implemented using optional variables.
Testing:
uncomment
```
unittest.skip("Local only - currently the qconv2d_cudnn op is bulid "
"with USE_EXPERIMENTAL_CUDNN_V8_API, we can enable the test "
"after it is built by default")
```
above test_qconv2d_cudnn in test/quantization/core/test_quantized_op.py.
Then execute
```
python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn
```
Differential Revision:
D34439768
D34439768
Test Plan: Imported from OSS
Reviewed By: jerryzh168
Pulled By: dzdang
fbshipit-source-id: 87f165411b6e8716f60f4048d249a1e1ae763325
(cherry picked from commit 2acf305b031969577ef04526d773c8c66ad3cb3a)
