Commits on Mar 28, 2023

1. [Vulkan] Add convert_qconv2d_context op (pytorch#97714) …

   Summary:
   Pull Request resolved: pytorch#97714
   
   This diffs adds a convert_qconv2d_context op, which converts a cpu quantized Conv2dPackedParamsBase object (used by quantized::conv2d) into a vulkan Conv2dPackedContext object.
   This op is used in a later diff (D44189363), to do a graph rewrite of quantized conv2d and conv2d_relu ops
   
   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: SS-JIA
   
   Differential Revision: D41595032
   
   fbshipit-source-id: fa1ae3e25237850b18c262891c6ae43d68ea8c7e

   

   manuelcandales authored and facebook-github-bot committed Mar 28, 2023
   Configuration menu

   • View commit details
   • Copy full SHA for 0bcd08f
   • Browse repository at this point

   Copy the full SHA

   0bcd08f View commit details

   Browse the repository at this point in the history