[Vulkan] Enable QInt8 weights and test quantized convolution with QInt8 weights and QInt32 bias (#90441)
Summary:
- Enable convolution with QInt8 weights
- Modify test_quantized_conv2d function to allow testing with QInt8 weights and QInt32 bias.
- Added multiple tests for regular, depthwise and pointwise convolution with QInt8 weights and QInt32 bias.
Test Plan:
On Mac
```
cd ~/fbsource
buck1 run -c pt.vulkan_full_precision=1 //xplat/caffe2:pt_vulkan_quantized_api_test_binAppleMac\#macosx-arm64
```
On Android
```
cd ~/fbsource
buck1 build -c ndk.custom_libcxx=false -c pt.enable_qpl=0 -c pt.vulkan_full_precision=1 //xplat/caffe2:pt_vulkan_quantized_api_test_binAndroid\#android-arm64 --show-output
adb push buck-out/gen/xplat/caffe2/pt_vulkan_quantized_api_test_binAndroid\#android-arm64 /data/local/tmp/vulkan_quantized_api_test
adb shell "/data/local/tmp/vulkan_quantized_api_test"
```
Reviewed By: kimishpatel
Differential Revision: D41562053
Pull Request resolved: https://github.com/pytorch/pytorch/pull/90441
Approved by: https://github.com/kimishpatel