ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Перейти к файлу
AtomicVar 5e5c36f6df
Fix citation author name issue (#19597)
Use `name` rather than `given-names` to set author name.

### Motivation and Context
The old CITATION.cff uses `given-names` to set author names, which won't
be rendered properly with some bibtex style of LaTeX:

<img width="680" alt="image"
src="https://github.com/microsoft/onnxruntime/assets/22856433/c509400e-5b16-4400-8950-550b05186369">

The problem is that **the `"ONNX Runtime developers"` is regarded as a
human name**.

How to fix: by using `name` to set author name, the generated Bibtex
entry will use `{}` to enclose the `"ONNX Runtime developers"`. Then it
is displayed literally:

<img width="742" alt="image"
src="https://github.com/microsoft/onnxruntime/assets/22856433/94083c9f-0daa-4c51-92e1-c966b88d09d2">
2024-02-22 17:03:56 -08:00
.config
.devcontainer
.gdn
.github
.pipelines
.vscode
cgmanifests
cmake [ROCm] Add SkipGroupNorm for ROCm EP (#19303) 2024-02-21 11:08:48 +08:00
csharp
dockerfiles
docs
include/onnxruntime/core
java [java] Adding ML program flag for CoreML (#19551) 2024-02-21 12:24:41 -08:00
js Bump ip from 1.1.8 to 1.1.9 in /js/react_native/e2e (#19583) 2024-02-22 13:58:17 -08:00
objectivec
onnxruntime Add special handling if there is only 1 graph inside the cached QNN context binary (#19594) 2024-02-22 13:15:13 -08:00
orttraining Move import to when needed to avoid circular dependency error (#19579) 2024-02-22 10:56:25 -08:00
rust
samples
tools [ROCm] Add SkipGroupNorm for ROCm EP (#19303) 2024-02-21 11:08:48 +08:00
winml Diable __cpuid call for ARM64EC (#19592) 2024-02-21 15:45:44 -08:00
.clang-format
.clang-tidy
.dockerignore
.gitattributes
.gitignore
.gitmodules
.lintrunner.toml
CITATION.cff Fix citation author name issue (#19597) 2024-02-22 17:03:56 -08:00
CODEOWNERS
CONTRIBUTING.md
LICENSE
NuGet.config
ORT_icon_for_light_bg.png
README.md
SECURITY.md
ThirdPartyNotices.txt
VERSION_NUMBER
build.bat
build.sh
build_arm64x.bat
lgtm.yml
ort.wprp
packages.config
pyproject.toml
requirements-dev.txt
requirements-doc.txt
requirements-lintrunner.txt
requirements-training.txt
requirements.txt.in
setup.py [ROCm] Add excluded libs for ROCm python package (#19586) 2024-02-22 13:34:55 +08:00

README.md

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 & Resources

Builtin Pipeline Status

System Inference Training
Windows Build Status
Build Status
Build Status
Linux Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Build Status
Mac Build Status
Android Build Status
iOS Build Status
Web Build Status
Other Build Status

Third-party Pipeline Status

System Inference Training
Linux 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.