* Add finetuned qdq options
* Add description
* Add unit tests
* Modify for channel axis
* Remove too specific feature. Move this implementation to e2e example
* Add OpTypesSupportPerChannelQuantization
* fix bug for unit test
* Keep flags OpTypesSupportPerChannelQuantization and QDQChannelAxis for internal use
Will have a follow-up PR to fine tune the code
* remove unnecessary warning
Co-authored-by: stevenlix <38092805+stevenlix@users.noreply.github.com>
Co-authored-by: Yufeng Li <liyufeng1987@gmail.com>
* fix reshape implementation in eager mode
* test code
* update opgen script to support fallback to cpu
* enhance the eager backend to support torch cpu fallback
* add more testes
* disable the printensor test for now, as we need to erge a PR to pytorch first
* Changes to ensure openvino build go through in Windows
* Modified Hetero plugin Logic
*Modified Hetero Feature logic. In Hetero,
if the operator to be marked true in getcapability(),
it should be supported by either of the devices
specified with HETERO in the device_type.
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* OV updated to 2021.4.2 version
* OV updated to 2021.4.2 version
* Updated OV to 2021.4.2 version, mono download link and dotnet version
* Copying Managed nugets in openvino c# docker file
*Copying Managed nuget to nugets artifacts
directory
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
Co-authored-by: saharfraza <sfatima.3001@gmail.com>
Co-authored-by: mayavijx <mayax.vijayan@intel.com>
Co-authored-by: Aravind Gunda <aravindx.gunda@intel.com>
* POWER10: Add optimized dgemm kernel
This patch makes use of POWER10 matrix multiply assist feature and
adds new DGEMM kernel.
* Indentation update
Co-authored-by: Rajalakshmi Srinivasaraghavan <rajis@linux.ibm.com>
- Only set them as targets for the ORT nuget package
- Use OrtPackageId as the condition for inclusion, if installed
- need to do the nuget restore via msbuild so that this property is set correctly
- Add desktop-only version of the C# sln as there is no way to exclude the mobile specific csproj's from an sln
- use this when applicable if someone is running build.py with the `--build_nuget` flag
Other
- remove attempt to include symbols in the nuget package as nuget doesn't support symbols in native packages
- update build.py to use `nuget` and not a windows specific path and filename for a linux build with `--build_nuget`
* es2017 by default for ort-common
* add visualizer and define plugin
* es2017 for ort-web. also add build target for es5
* add multiple reduced size build for ort-web
* resolve comments, add e2e tests and add docs
* fix segmentation fault
* fix typo
* fix bug
* make logic the same as CUDA ep
* Modify for OpenVINO
* Add env variable check for OpenVIO
* refine the code
* refine EP failed registration warning messages.
* update OpenVINO exception message.
Co-authored-by: George Wu <jywu@microsoft.com>
* Implementaiton of Squeeze op for dnnl ep
Signed-off-by: George Nash <george.nash@intel.com>
* Implementaiton of Unsqueeze op for dnnl ep
Tests were added to the unsqueeze_op_test to test Unsqueeze op
with a scalar input.
The OneDNN (dnnl) ep automatically converts scalars to a one dimentional
tensor. For most operations this causes no problems. However, for
Unsqueeze the difference between a scalar vs. tensor couldn't be
ignored. A IsScalar member function was added to the DnnlSubgrapPrimitive
class that will return true if the ORT tensor was a scalar type. IsScalar()
is then used inside the Unsqueeze code.
updated the squeeze node capability to only accept ConstantInitializer
inputs.
All unsqueeze op tests that tested opset 13 now run with and without
constant initializers.
Signed-off-by: George Nash <george.nash@intel.com>
