saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-06-24 02:47:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
9231 commits 2856 branches 57 tags 1.3 GiB
C++ 87.3%
Python 3.1%
C 2.4%
PureBasic 2%
C# 1%
Other 3.7%
Find a file
raoanag 34b6cd6d9a
MatMulIntToFloat Enable FP16 and update tensor ORT-DML indexing (#16871) 
MatMulIntegerToFloat Enable FP16 and update tensor ORT-DML indexing

```
.\onnxruntime_test_all.exe --gtest_filter="*MatMulIntegerToFloat*"
Note: Google Test filter = *MatMulIntegerToFloat*
[==========] Running 13 tests from 4 test suites.
[----------] Global test environment set-up.
[----------] 1 test from CPU_U8S8_Precision_Tests
[ RUN      ] CPU_U8S8_Precision_Tests.MatMulIntegerToFloat
[       OK ] CPU_U8S8_Precision_Tests.MatMulIntegerToFloat (35 ms)
[----------] 1 test from CPU_U8S8_Precision_Tests (35 ms total)

[----------] 1 test from GraphTransformationTests
[ RUN      ] GraphTransformationTests.MatMulIntegerToFloatTest
[       OK ] GraphTransformationTests.MatMulIntegerToFloatTest (5 ms)
[----------] 1 test from GraphTransformationTests (5 ms total)

[----------] 1 test from QDQTransformerTests
[ RUN      ] QDQTransformerTests.MatMulIntegerToFloat
[       OK ] QDQTransformerTests.MatMulIntegerToFloat (24 ms)
[----------] 1 test from QDQTransformerTests (24 ms total)

[----------] 10 tests from MatMulIntegerToFloat
[ RUN      ] MatMulIntegerToFloat.HasZeroPoint_NoBias_test_U8X8_FP16
2023-07-27 16:45:13.1564552 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:13.3115187 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:13.4173384 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:13.5232503 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:13.6350011 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:13.7389236 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:13.8479674 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:13.9661708 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
[       OK ] MatMulIntegerToFloat.HasZeroPoint_NoBias_test_U8X8_FP16 (951 ms)
[ RUN      ] MatMulIntegerToFloat.NoZeroPoint_HasBias_test_U8X8_FP16
2023-07-27 16:45:14.1087648 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:14.2124719 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:14.3137829 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:14.4173078 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:14.5223567 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:14.6240616 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:14.7247578 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:14.8346170 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
[       OK ] MatMulIntegerToFloat.NoZeroPoint_HasBias_test_U8X8_FP16 (830 ms)
[ RUN      ] MatMulIntegerToFloat.HasZeroPoint_NoBias_test_S8S8_FP16
2023-07-27 16:45:14.9395745 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:15.0389962 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:15.1365449 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:15.2336207 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
[       OK ] MatMulIntegerToFloat.HasZeroPoint_NoBias_test_S8S8_FP16 (393 ms)
[ RUN      ] MatMulIntegerToFloat.NoZeroPoint_HasBias_test_S8S8_FP16
2023-07-27 16:45:15.3304154 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:15.4340044 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:15.5331474 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
2023-07-27 16:45:15.6337272 [W:onnxruntime:Default, base_tester.cc:763 onnxruntime::test::BaseTester::ExecuteModelForEps] registered execution providers CPUExecutionProvider were unable to run the model.
[       OK ] MatMulIntegerToFloat.NoZeroPoint_HasBias_test_S8S8_FP16 (403 ms)
[ RUN      ] MatMulIntegerToFloat.HasZeroPoint_NoBias_test_U8X8
[       OK ] MatMulIntegerToFloat.HasZeroPoint_NoBias_test_U8X8 (739 ms)
[ RUN      ] MatMulIntegerToFloat.NoZeroPoint_HasBias_test_U8X8
[       OK ] MatMulIntegerToFloat.NoZeroPoint_HasBias_test_U8X8 (756 ms)
[ RUN      ] MatMulIntegerToFloat.HasZeroPoint_NoBias_test_S8S8
[       OK ] MatMulIntegerToFloat.HasZeroPoint_NoBias_test_S8S8 (363 ms)
[ RUN      ] MatMulIntegerToFloat.NoZeroPoint_HasBias_test_S8S8
[       OK ] MatMulIntegerToFloat.NoZeroPoint_HasBias_test_S8S8 (368 ms)
[ RUN      ] MatMulIntegerToFloat.MatMulInteger_With_ZeroPoint
[       OK ] MatMulIntegerToFloat.MatMulInteger_With_ZeroPoint (11 ms)
[ RUN      ] MatMulIntegerToFloat.MatMulInteger_With_ZeroPoint_FP16
[       OK ] MatMulIntegerToFloat.MatMulInteger_With_ZeroPoint_FP16 (11 ms)
[----------] 10 tests from MatMulIntegerToFloat (4833 ms total)

[----------] Global test environment tear-down
[==========] 13 tests from 4 test suites ran. (4914 ms total)
[  PASSED  ] 13 tests.
```
2023-07-28 14:45:49 -07:00
.config Update tsaoptions.json: update the email alias (#13448) 2022-10-26 15:56:16 -07:00
.devcontainer Remove two lines in the Dockerfile for Github Codespace (#12278) 2022-07-21 20:52:17 -07:00
.gdn Update win-ci-pipeline.yml: enable xnnpack tests (#16244) 2023-06-14 19:12:42 -07:00
.github Bump actions/deploy-pages from 1 to 2 (#16402) 2023-07-24 16:13:59 -07:00
.pipelines Workaround to upgrade VS2022 for Windows ARM build (#16826) 2023-07-25 08:35:52 +08:00
.vscode cpplint & Eager mode: refactor and add comments to empty_* functions, general lint cleanup in ort_aten (#12238) 2022-07-20 11:47:57 -04:00
cgmanifests [TensorRT EP] TRT 8.6 minor version update (#16475) 2023-06-26 10:44:27 -07:00
cmake Workaround to upgrade VS2022 for Windows ARM build (#16826) 2023-07-25 08:35:52 +08:00
csharp Change DML GPU pool in Windows GPU workflow use Visual Studio 2022 (#16784) 2023-07-23 10:07:21 +08:00
dockerfiles Enable model subgraph execution in OVEP and setting the OpenVINO dll's to the path from the OpenVINO pypi packge in OVEP and fix OVEP windows io buffer sample (#16147) 2023-06-16 19:47:09 -07:00
docs [Better Engineering] Bump ruff to 0.0.278 and fix new lint errors (#16789) 2023-07-21 12:53:41 -07:00
include/onnxruntime/core Fix bug with saving model optimized by inference session (#16716) 2023-07-20 18:44:28 -07:00
java [java] Fp16 fix for android/react native (#16832) 2023-07-25 12:31:32 -07:00
js Bump word-wrap from 1.2.3 to 1.2.4 in /js/react_native (#16755) 2023-07-22 13:36:49 -07:00
objectivec Objective-C Add Support to Create and Query String ORTValues (#16764) 2023-07-20 17:39:29 -07:00
onnxruntime MatMulIntToFloat Enable FP16 and update tensor ORT-DML indexing (#16871) 2023-07-28 14:45:49 -07:00
orttraining [DORT] Enable Dynamic Shape in DORT and Use Different InferenceSession's when Inputs Are Not Compatible (#16753) 2023-07-24 16:54:01 -07:00
rust Add rust bindings (#12606) 2023-02-08 14:57:15 -08:00
samples Enable pylint and numpy rules (#15218) 2023-03-27 20:37:53 -07:00
swift/OnnxRuntimeBindingsTests Add iOS Swift Package Manager support (#15297) 2023-04-20 16:18:35 +10:00
tools Update upload_pod_archive_and_update_podspec.sh to take path pattern (#16810) 2023-07-25 08:55:31 -07:00
winml [WinML] Fix warnings in OnnxruntimeEngine and OnnxruntimeEngineBuilder (#16679) 2023-07-12 13:09:50 -07:00
.clang-format Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
.clang-tidy Create clang-tidy CI (#12653) 2022-09-30 08:05:38 -07:00
.dockerignore
.gitattributes
.gitignore remove 'lib/' from .gitignore (#15613) 2023-04-24 18:43:32 -07:00
.gitmodules Update eigen to 3.4 and remove the eigen from git submodule (#15875) 2023-05-11 11:56:59 -07:00
.lintrunner.toml Minimal Build for On-Device Training (#16326) 2023-06-22 12:27:23 -07:00
build.bat Upgrade old Python version in packaging pipeline (#16667) 2023-07-17 08:24:47 -07:00
build.sh Upgrade old Python version in packaging pipeline (#16667) 2023-07-17 08:24:47 -07:00
CITATION.cff
CODEOWNERS Add owners for public facing API files (#15288) 2023-03-30 17:16:15 -07:00
CONTRIBUTING.md Fix link to High Level Design (#11786) 2023-02-28 11:05:54 -08:00
lgtm.yml Fix lgtm C++ error (#13613) 2022-11-10 10:06:22 -08:00
LICENSE
NuGet.config
ort.wprp
ORT_icon_for_light_bg.png
Package.swift Objective-C Add Support to Create and Query String ORTValues (#16764) 2023-07-20 17:39:29 -07:00
packages.config [DML EP] Update DirectML version to 1.12.0 (#16011) 2023-05-18 19:37:12 -07:00
pyproject.toml [Better Engineering] Bump ruff to 0.0.278 and fix new lint errors (#16789) 2023-07-21 12:53:41 -07:00
README.md add third-party pipeline status to README.md (#16155) 2023-05-31 22:14:39 -07:00
requirements-dev.txt Remove codecov from requirements-dev.txt (#15487) 2023-04-12 18:48:02 -07:00
requirements-doc.txt
requirements-lintrunner.txt [Better Engineering] Bump ruff to 0.0.278 and fix new lint errors (#16789) 2023-07-21 12:53:41 -07:00
requirements-training.txt Remove protobuf pin from training requirements (#13695) 2022-11-22 12:27:18 -08:00
requirements.txt.in
SECURITY.md Microsoft mandatory file (#11619) 2022-05-25 13:56:10 -07:00
setup.py Triton Codegen for ORTModule (#15831) 2023-07-13 18:17:58 +08:00
ThirdPartyNotices.txt Implement openAI endpoint invoker for nuget (#15797) 2023-05-11 22:04:02 -07:00
VERSION_NUMBER Update VERSION_NUMBER (#15773) 2023-05-03 15:07:34 -07:00

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
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.