Chen Fu 1c84621020 Adding ARM64 depthwise convolution kernel for symmetric quantization (#9655) ... Adding ARM64 depthwise convolution kernel for symmetric quantization Motivation and Context Two improvements against current kernel code : 1. Signed int8 based instructions, no need to extend from 8b to 16b before multiplication. 2. Unrolled loop with manual software pipelining Co-authored-by: Chen Fu <fuchen@microsoft.com>		2021-11-15 12:18:43 -08:00
..
docker	Update training pipelines to pytorch 1.10 (#9709)	2021-11-15 11:21:55 -08:00
ort_minimal	Adding ARM64 depthwise convolution kernel for symmetric quantization (#9655)	2021-11-15 12:18:43 -08:00
build_yocto.sh	Bring code coverage dashboard back (#8394)	2021-08-16 20:54:39 -07:00
copy_strip_binary.sh	Move one function from cuda_provider_factory.h (#8407)	2021-07-19 17:55:59 -07:00
create_package.sh	Pull the latest image before running docker build	2019-11-22 13:48:37 -08:00
extract_and_bundle_gpu_package.sh	Add Xamarin support (#9436)	2021-10-27 20:07:07 +10:00
java_copy_strip_binary.sh	Add Linux/MacOS ARM64 support to nuget packaging pipeline (#9570)	2021-10-27 19:00:43 -07:00
java_linux_final_test.sh	Delete Dockerfile.centos6_gpu (#4851)	2020-08-28 09:56:52 -07:00
run_build.sh	Delete Dockerfile.ubuntu_for_android (#8848)	2021-08-25 22:25:14 -07:00
run_dockerbuild.sh	Delete Dockerfile.ubuntu_for_android (#8848)	2021-08-25 22:25:14 -07:00
test_custom_ops_pytorch_export.sh	Change "Export PyTorch CustomOp" build pipeline to use Ubuntu 20.04 (#8158)	2021-06-28 16:13:55 -07:00
upload_code_coverage_data.sh	Bring code coverage dashboard back (#8394)	2021-08-16 20:54:39 -07:00
upload_ortsrv_binaries.sh
yocto_build_toolchain.sh	Bring code coverage dashboard back (#8394)	2021-08-16 20:54:39 -07:00