* If unit tests are manually excluded via `--cmake_extra_defines onnxruntime_BUILD_UNIT_TESTS=OFF` (e.g. testing changes to binary size where you want to keep the build time as quick as possible) it should still be possible to create the python bindings.
Update CMakeLists.txt to decouple the inclusion of onnxruntime_python.cmake from unit tests being enabled.
Update onnxruntime_python.cmake so it works when unit tests are disabled. Also skip copying of test py files when unit tests are disabled.
* Add robust dependency check for Python package
* Add version_info.py to .gitignore
* Fix Linux build
* Fix Windows CPU build
* Fix Windows 32-bit build
* Minor tweak
* Generate version_info.py earlier in onnxruntime_python.cmake
* Print a user-friendly message if cuDNN is not found in
* Relax version requirements for CUDA 11 - only the major version has to match
* Fix PATH environment variable to include CUDA 11 in 'Python packaging pipeline' (Windows/GPU)
* Fix the build with cuDNN 7
ONNX Runtime 1.7 will the last release that will publish MCR
container images for ONNX Runtime with OpenVINO EP. From ONNX
Runtime 1.8 onwards, this will be discontinued. Users are advised
to switch to using PyPi packages or build their own containers
using dockerfiles.
* Fixes OpenVINO-EP windows build
Openvino EP build is broken on windows. The issue
is wchar_t is UTF-16 on windows while on other platforms
such as Linux and MacOS, wchar_t is UTF-32.
so wide Unicode string has to be converted to an UTF8 string
for sure on windows.
This commit fixes this issue.
* Add support for custom ops library to the ORT model conversion script
Simplify model conversion now that we read ops from the ORT format model.
Enable custom ops in the python bindings if custom ops are turned on in a minimal build.
* Add test of model conversion involving custom ops.
* Integrate memory improvements from NVidia
* compute max_global_num before buffer allocation
* update conversion script to support transformers 4.0
* update benchmark script for creating dummy inputs for different batch_size
* Use a wrapper of cuda event to avoid memory leak
* rename pipelines
* resync and rename
* resync master
* rename package id
* remove OrtPackageId which is for nuget
Co-authored-by: Randy Shuai <rashuai@microsoft.com>
* Adding changes to enable ov_config_options
Enabling a flag to pass OpenVINO Runtime options
as an string argument using a command line.
* Enabling OpenVINO Runtime options for perftest
Enables OpenVINO EP runtime options into onnxruntime_perf_test.
Now these options can be passed as an argument to the perf test CPP
application using key-value pairs seperated by a space via a
command line.
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* minor changes added
* Corrected Indentation
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* corrected Indendation issues
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
* Making config options generic to all EP's
Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>
1. For previous openmp build, remove --use_openmp, so thread pool will become default;
2. For previous non-openmp build, add --use_openmp and rename the package to indicate the inclusion.
3. Add a mac build with openmp enabled.
