ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Find a file
Suffian Khan 4daa14bc74
Fixes to rel-1.9.0 to compile and pass for AMD ROCm (#9144)
* Revert "Fix nightly CI pipeline to generate ROCm 4.2 wheels and add ROCm 4.3.1 wheels (#9101)"

This reverts commit 47888392ab.

* Add BatchNorm kernel for ROCm (#9014)

* Add BatchNorm kernel for ROCm, update BN test

* correct epsilon_ setting; limit min epsilon

* Upgrade ROCm CI pipeline for ROCm 4.3.1 and permit run inside container (#9070)

* try to run inside 4.3.1 container

* no \ in container run command

* remove networking options

* try with adding video render groups

* add job to build docker image

* try without 1st stage

* change alpha, beta to float

* try adding service connection

* retain huggingface directory

* static video and render gid

* use runtime expression for variables

* install torch-ort

* pin sacrebleu==1.5.1

* update curves for rocm 4.3.1

* try again

* disable determinism and only check tail of loss curve and with a much larger threshold of 0.05

* disable RoBERTa due to high run variablity on ROCm 4.3.1

* put reduction unit tests back in

* Fix nightly CI pipeline to generate ROCm 4.2 wheels and add ROCm 4.3.1 wheels (#9101)

* make work for both rocm 4.2 and rocm 4.3.1

* fix rocm 4.3.1 docker image reference

* fix CUDA_VERSION to ROCM_VERSION

* fix ReduceConsts conflict def

* add ifdef to miopen_common.h as well

* trailing ws

Co-authored-by: wangye <wangye@microsoft.com>
Co-authored-by: mindest <30493312+mindest@users.noreply.github.com>
2021-09-21 18:07:07 -07:00
.gdn Update compliance tasks in python packaging pipeline and fix some compile warnings (#8471) 2021-07-30 17:16:37 -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 Second round cherry-pick to rel-1.9.0 (#9062) 2021-09-15 18:02:07 -07:00
cmake Final round cherry-picks to 1.9.0 (#9133) 2021-09-21 12:18:03 -07:00
csharp Final round cherry-picks to 1.9.0 (#9133) 2021-09-21 12:18:03 -07:00
dockerfiles Change cmake_cuda_architectures to double quotes (#8990) 2021-09-08 09:41:52 -07:00
docs Second round cherry-pick to rel-1.9.0 (#9062) 2021-09-15 18:02:07 -07:00
include/onnxruntime/core Final round cherry-picks to 1.9.0 (#9133) 2021-09-21 12:18:03 -07:00
java Add NNAPI E2E test for Android java package (#8912) 2021-08-31 17:34:33 -07:00
js Second round cherry-pick to rel-1.9.0 (#9062) 2021-09-15 18:02:07 -07:00
objectivec [Objective-C] Enable static analysis, second try (#8875) 2021-08-30 10:43:45 -07:00
onnxruntime Fixes to rel-1.9.0 to compile and pass for AMD ROCm (#9144) 2021-09-21 18:07:07 -07:00
orttraining Fixes to rel-1.9.0 to compile and pass for AMD ROCm (#9144) 2021-09-21 18:07:07 -07:00
package/rpm bumping up to version 1.9 (#8982) 2021-09-07 14:30:55 -07:00
samples Add Python checks pipeline (#7032) 2021-08-09 10:37:05 -07:00
server fix boost download url (#7843) 2021-05-26 16:08:57 -07:00
tools Fixes to rel-1.9.0 to compile and pass for AMD ROCm (#9144) 2021-09-21 18:07:07 -07:00
winml Add new option to disable cpu sync for tensors (#8490) 2021-08-27 13:29:52 -07:00
.clang-format Initial bootstrap commit. 2018-11-19 16:48:22 -08:00
.clang-tidy Add remaining build options and make minor changes in documentation (#39) 2018-11-27 19:59:40 -08:00
.dockerignore Update dockerfiles (#5929) 2020-11-25 15:38:22 -08:00
.flake8 Add Python checks pipeline (#7032) 2021-08-09 10:37:05 -07:00
.gitattributes Initial bootstrap commit. 2018-11-19 16:48:22 -08:00
.gitignore Add netstandard2.0 framework to nuget managed package. (#8960) 2021-09-04 08:01:46 +10:00
.gitmodules [js/web] update emsdk to v2.0.26 (#8653) 2021-08-26 15:31:34 -07:00
build.amd64.1411.bat Initial bootstrap commit. 2018-11-19 16:48:22 -08:00
build.bat Initial bootstrap commit. 2018-11-19 16:48:22 -08:00
build.sh Add iOS test pipeline and a sample app. (#5298) 2020-09-29 13:53:11 -07:00
CODEOWNERS Update CODEOWNERS with mobile team ownership of expected kernel def hash data files. (#8454) 2021-07-22 11:19:06 -07:00
CONTRIBUTING.md fixed the link (#8757) 2021-08-18 11:45:42 -07:00
LICENSE Remove year from license (#6658) 2021-02-12 00:25:56 -08:00
NuGet.config Delete nuget extra configs (#6477) 2021-01-27 20:25:45 -08:00
ort.wprp Add Tracelogging for profiling (#1639) 2019-11-11 21:34:10 -08:00
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 typo 2021-08-12 15:57:15 -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 python manylinux to not load cuda if it fails to load dependencies (#8882) 2021-09-07 11:09:25 -07:00
ThirdPartyNotices.txt Extend node debugging utilities to push tensors and node placement to SQL database (#8672) 2021-08-21 00:40:12 -07:00
VERSION_NUMBER bumping up to version 1.9 (#8982) 2021-09-07 14:30:55 -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

General Information: onnxruntime.ai

Usage documention and tutorials: onnxruntime.ai/docs

Companion sample repositories:

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.