* initial implementation of longformer tools for onnx conversion and benchmark
* Support ONNX conversion for transformers 4.0
Add an option to optimize onnx model, and export fp16 model
* improves processing time by 10
* extend coverage unit test coverage
* better implementation for the multi regression case
* better comment, keep parallelization by trees when not enough trees
MatMulIntegerToFloat fusion fuses per-row and per-column MatMulInteger, which is not supported by the MatMulIntegerToFloat kernel now. Limit the fusion to per-matrix only before we supporting the per-channel fully.
* Add support for non-1d tensor for C of Gemm
* check android api level before add squeeze
* Minor update
* Fix to accept c only in format of {1,1,...,1,n}
* Add suspend handler with new telemetry event
* Fix build warning
* Use cppwinrt from nuget
* Restore nuget packages
* add dependencies
* Add nuget_helpers
* Cleaned up
* Clean up
* Comment
* Add dependencies for the rest
* Remove unused line
* Update activation string
* PR comment to remove ALL
* Expand the documentation on using compiling EPs with a minimal build to call out a 'simple' option that is easier to use. Provide more background on what happens to help users choose the best option for them.
Tweak conversion script to be noisier about attempted usage of 'all' optimization level.
Co-authored-by: manashgoswami <magoswam@microsoft.com>
* optimize a bert model converted using tf2onnx
* add test data
* update
* remove comments
* format
* Revert "format"
This reverts commit f8ae88cb564bce5caf4780e56561403f3ba3d524.
* Revert "remove comments"
This reverts commit 59d8a693581a731fd0291b70fe2c9cec6c4950fe.
* add a squeeze node to convert a 3-d mask to 2-d
* update
* update
* verify and add comments
1. Make sure to free the output_shape vector even if Output names mismatch between OpenVINO and ONNX exception is thrown
2. Piggy back this PR to remove un-needed call to fstream close method
Authored-by: modav <modav@microsoft.com>
* Enable scalar input for NNAPI EP
* Map scalar output ({1} tensor) of NNAPI back to scalar ({} tensor) if necessary
* Enforce NNAPI scalar output has {1} shape
* address CR comments
* minor update
1. Remove conda from the images. Because conda contains a file named /opt/miniconda/lib/libcrypto.so.1.0.0 which can't pass our security scan. Also, it will be easier for us to manage the third party usage registrations.
2. Remove openssh from the images. Because the official openssh package provided by Ubuntu can't pass our security scan.
3. Reduce the image size to 1/3 by using stages. Also, because it contains less packages, it will be less often needed to update.
4. Put the LICENSE-IMAGE.txt file in right place. It is missed in current images. You can see it was added to a temp folder "/code" but it got deleted afterwards.
5. Update the CPU docker image's base image to Ubuntu 18.04. The GPU one is already 18.04. It's better to keep them the same.
6. Remove the build arg ONNXRUNTIME_REPO/ONNXRUNTIME_BRANCH. Instead, the new one always uses the local source. I feel it can reduce confusion.
* Update OpenVINO-ExecutionProvider.Md
update openvino-executionprovider.md for shared library
* Update Build.md
updated --build_shared_lib flag for building openvino shared provider lib
* Update Dockerfile.openvino
building for shared library with the new changes for openvino shared lib
* Revert "Update Build.md"
This reverts commit c9cf5fee76be7fdc10cadf07259f1d4ed5b45b93.
* Revert "Update Dockerfile.openvino "
This reverts commit e1624e4f93a4cfb425b6f21d7fb71b299a146740.
* Update OpenVINO-ExecutionProvider.md
fix documentation to the shared library
Co-authored-by: sfatimar <sahar.fatima@intel/com>
