* add ortmodule and eager mode test
* add ortmodule dependency
* fix eager pipeline
* skip tthe ortmodule test for windows due to win ci issue
* remove useless win ci change
* add torch
Co-authored-by: Abhishek Jindal <abjindal@microsoft.com>
* Op fusion support added
In addition the following op fusions are detected
- ConvRelu
- MatMulAdd
This change includes
- Change abstraction of Subgraph + node + tensor to support delete insert
modify
- add nodearg class to establish connection from tensor to node
- add graphtransformer class to support fusion
- add topological sort to ensure propoer node ordering after fusion
- add convrelu + matmuladd primitive to support execution of fused nodes
- Fix FusionResolution with missing tensors
when fusing, if the target node contains fewer tensors then original
patterns (Gelu and FastGelu ignores many initializers), potentially delete them
also from inputs and initializers
Also check tensor has no producer and consumer before deleting
Signed-off-by: Wang <zhaoyang.wang@intel.com>
* Gelu and FastGelu Fusion for DNNL EP
The basics of the Gelu/FastGelu code is modeled after:
- core/optimizer/fast_gelu_fusion.cc and
- core/optimizer/gelu_fusion.cc
OneDNN does not have support for 'Erf' unless it is part of 'Gelu'.
This results in detecting 'Gelu' fusion twice. Once when detecting
if the 'Erf' Operator is supported and again in the subgraph transformer
code. The capability code is finding the Gelu using onnxruntime:GraphViewer
and onnxruntime::Node. While the transformer code is using DnnlSubgraph
and DnnlNode. This results in two parts of code looking for the same
pattern but unfortanatly having little code reuse.
This also adds support for Biased versions of Gelu and FastGelu if they already
exist in a model.
Signed-off-by: George Nash <george.nash@intel.com>
* Code Clean Up
Signed-off-by: Wang <zhaoyang.wang@intel.com>
Co-authored-by: Wang <zhaoyang.wang@intel.com>
* Add 2 builds to validate the cmake defines for excluding optional components work in both full and minimal builds.
* Create empty config for no-ops build
* Create empty config for no-ops build - attempt #2
* Create empty config for no-ops build - attempt #3
* Update python binding code to work when sparse tensors are disabled.
* 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
