ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Find a file
Tang, Cheng 598454bb5f
Fix the mix precision handle for square case (#8333)
* handle unsqueeze change in opset13

* fix the node arguments index check for square case (x * x)

* Revert "fix the node arguments index check for square case (x * x)"

This reverts commit c66344f0a82c35d8c24d31f2264cf7e9b235ce22.

* handle the square case (x * x) for node argument search

Co-authored-by: Cheng Tang <chenta@microsoft.com>
2021-07-09 09:24:19 -07:00
.github Update issue template to ask users to check known issues to avoid repetition. (#8288) 2021-07-02 15:36:14 -07:00
cgmanifests Update C++ Standard from 14 to 17 (#8041) 2021-06-25 14:08:01 -07:00
cmake Refactor QDQ optimizers to enable future usage in minimal build (#8191) 2021-07-09 16:11:43 +10:00
csharp Enable TRT provider option configuration for C# (updated version) (#7808) 2021-06-25 03:21:22 -07:00
dockerfiles Update migraphx to rocm4.2 (#7994) 2021-06-22 13:39:51 -07:00
docs Support SpaceDepth ops in the CUDA and ROCM EPs (#7960) 2021-07-09 01:00:22 -07:00
include/onnxruntime/core Enable cast propagation with level one by default. (#8286) 2021-07-08 14:38:09 -07:00
java [Java] Fixing the creation of OnnxTensors from scalars, adding tests (#8023) 2021-06-24 13:21:35 -07:00
js Adding optional ops in contrib ops (#7946) 2021-06-24 13:16:31 -07:00
objectivec [Objective-C API] Add support for documentation generation (#7999) 2021-06-11 17:49:00 -07:00
onnxruntime [CoreML EP] Add Int32<->Int64 handling around coreml ep (#8183) 2021-07-09 09:08:05 -07:00
orttraining Fix the mix precision handle for square case (#8333) 2021-07-09 09:24:19 -07:00
package/rpm bumping up version number to 1.8 (#7733) 2021-05-18 09:03:37 -07:00
samples Add post-install command to build PyTorch CPP extensions from within onnxruntime package (#8027) 2021-06-28 18:11:58 -07:00
server fix boost download url (#7843) 2021-05-26 16:08:57 -07:00
tools Support SpaceDepth ops in the CUDA and ROCM EPs (#7960) 2021-07-09 01:00:22 -07:00
winml Implement WINRT_IMPL_LoadLibraryW to avoid calling LoadLibraryW directly (#8065) 2021-06-22 14:31:20 -07:00
.clang-format
.clang-tidy
.dockerignore
.flake8
.gitattributes
.gitignore Add auto doc gen for ORTModule API during CI build (#7046) 2021-03-22 10:20:33 -07:00
.gitmodules Integrate onnxruntime-extensions into onnxruntime. (#8143) 2021-07-01 09:34:03 -07:00
build.amd64.1411.bat
build.bat
build.sh
CODEOWNERS Add myself to CODEOWNERS for ORTModule python code (#7453) 2021-05-07 15:35:45 -07:00
CONTRIBUTING.md Add README for docs (#6626) 2021-03-12 15:14:40 -08:00
LICENSE
NuGet.config
ort.wprp
packages.config Update DirectML version to 1.5.1 and enable ARM/ARM64 builds with DML (#7511) 2021-04-30 00:49:30 -07:00
README.md Fix readme page (#7659) 2021-05-12 14:30:23 -07:00
requirements-dev.txt Add post-install command to build PyTorch CPP extensions from within onnxruntime package (#8027) 2021-06-28 18:11:58 -07:00
requirements-doc.txt Add auto doc gen for ORTModule API during CI build (#7046) 2021-03-22 10:20:33 -07:00
requirements-training.txt Add post-install command to build PyTorch CPP extensions from within onnxruntime package (#8027) 2021-06-28 18:11:58 -07:00
requirements.txt.in Chang how numpy version is handled. (#8130) 2021-06-23 14:08:37 -07:00
setup.py fix ld_preload for rocm (#8290) 2021-07-02 17:15:28 -07:00
ThirdPartyNotices.txt ONNX Runtime React Native Library (#7564) 2021-05-11 10:34:40 -07:00
VERSION_NUMBER bumping up version number to 1.8 (#7733) 2021-05-18 09:03:37 -07:00

ONNX Runtime is a cross-platform inference and training machine-learning accelerator.

ONNX Runtime inference can enable faster customer experiences and lower costs, supporting models from deep learning frameworks such as PyTorch and TensorFlow/Keras as well as classical machine learning libraries such as scikit-learn, LightGBM, XGBoost, etc. ONNX Runtime is compatible with different hardware, drivers, and operating systems, and provides optimal performance by leveraging hardware accelerators where applicable alongside graph optimizations and transforms. Learn more →

ONNX Runtime training can accelerate the model training time on multi-node NVIDIA GPUs for transformer models with a one-line addition for existing PyTorch training scripts. Learn more →

Get Started

http://onnxruntime.ai/

Build Pipeline Status

System CPU GPU EPs
Windows Build Status Build Status Build Status
Linux Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Mac Build Status
Build Status
Android Build Status
iOS Build Status
WebAssembly Build Status

Data/Telemetry

Windows distributions of this project may collect usage data and send it to Microsoft to help improve our products and services. See the privacy statement for more details.

Contributions and Feedback

We welcome contributions! Please see the contribution guidelines.

For feature requests or bug reports, please file a GitHub Issue.

For general discussion or questions, please use Github Discussions.

Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

License

This project is licensed under the MIT License.