f2694ab526
* Update provider_test_utils.cc * Update tensorrt_execution_provider.h * Update tensorrt_execution_provider.cc * Update gemm_test.cc * Update softmax_test.cc * Update logsoftmax_test.cc * Update matmul_test.cc * Update batch_norm_op_test.cc * Update conv_op_test.cc * Update batch_norm_op_test.cc * Update softmax_test.cc * Update conv_transpose_op_test.cc * Update instance_norm_op_test.cc * Update flatten_op_test.cc * Update loop_test.cc * Disable failed tests for TensorRT * Disable unsupported tests for TensorRT * Disable unsupported tests for TensorRT * Disable unsupported tests for TensorRT * Disable unsupported tests for TensorRT * Update matmul_test.cc * Update logsoftmax_test.cc * Update topk_op_test.cc * disable unsupported tests for TensorRT * resolve conflicts * Update identity_op_test.cc * Update activation_op_test.cc * make max batch size configurable and simplify the code for disabling unsupported tests * make max batch size configurable at runtime * update tensorrt ci pipline * move max batch size to private * Update tensorrt_execution_provider.cc * Update tensorrt_execution_provider.h * Update tensorrt_execution_provider.cc * add comments on the test changes * Update tensorrt_execution_provider.h * Update tensorrt_execution_provider.cc * Update build.py |
||
|---|---|---|
| .github/ISSUE_TEMPLATE | ||
| cmake | ||
| csharp | ||
| dockerfiles | ||
| docs | ||
| include/onnxruntime/core | ||
| onnxruntime | ||
| package/rpm | ||
| tools | ||
| .clang-format | ||
| .clang-tidy | ||
| .gitattributes | ||
| .gitignore | ||
| .gitmodules | ||
| build.amd64.1411.bat | ||
| build.bat | ||
| BUILD.md | ||
| build.sh | ||
| cgmanifest.json | ||
| CODEOWNERS | ||
| CONTRIBUTING.md | ||
| LICENSE | ||
| README.md | ||
| rename_manylinux.sh | ||
| requirements-dev.txt | ||
| requirements-doc.txt | ||
| requirements.txt | ||
| setup.py | ||
| TensorRT-ExecutionProvider.md | ||
| ThirdPartyNotices.txt | ||
| VERSION_NUMBER | ||
ONNX Runtime is an open-source scoring engine for Open Neural Network Exchange (ONNX) models.
ONNX is an open format for machine learning (ML) models that is supported by various ML and DNN frameworks and tools. This format makes it easier to interoperate between frameworks and to maximize the reach of your hardware optimization investments. Learn more about ONNX on https://onnx.ai or view the Github Repo.
Why use ONNX Runtime
ONNX Runtime is an open architecture that is continually evolving to adapt to and address the newest developments and challenges in AI and Deep Learning. We will keep ONNX Runtime up to date with the ONNX standard, supporting all ONNX releases with future compatibliity while maintaining backwards compatibility with prior releases.
ONNX Runtime continuously strives to provide top performance for a broad and growing number of usage scenarios in Machine Learning. Our investments focus on these 3 core areas:
- Run any ONNX model
- High performance
- Cross platform
Run any ONNX model
Alignment with ONNX Releases
ONNX Runtime provides comprehensive support of the ONNX spec and can be used to run all models based on ONNX v1.2.1 and higher. See ONNX version release details here.
As of March 2019, ONNX Runtime supports ONNX 1.4.
Traditional ML support
ONNX Runtime fully supports the ONNX-ML profile of the ONNX spec for traditional ML scenarios.
High Performance
You can use ONNX Runtime with both CPU and GPU hardware. You can also plug in additional execution providers to ONNX Runtime. With many graph optimizations and various accelerators, ONNX Runtime can often provide lower latency and higher efficiency compared to other runtimes. This provides smoother end-to-end customer experiences and lower costs from improved machine utilization.
Currently ONNX Runtime supports CUDA, MLAS (Microsoft Linear Algebra Subprograms), MKL-DNN, and MKL-ML for computation acceleration. See more details on available build options here or refer to this page to add a new execution provider.
We are continuously working to integrate new execution providers to provide improvements in latency and efficiency. We have ongoing collaborations to integrate the following with ONNX Runtime:
- Intel MKL-DNN and nGraph
- NVIDIA TensorRT
Cross Platform
ONNX Runtime offers:
- APIs for Python, C#, and C
- Available for Linux, Windows, and Mac
See API documentation and package installation instructions below.
Looking ahead: To broaden the reach of the runtime, we will continue investments to make ONNX Runtime available and compatible with more platforms. If you have specific scenarios that are not currently supported, please share your suggestions via Github Issues.
Getting Started
If you need a model:
- Check out the ONNX Model Zoo for ready-to-use pre-trained models.
- To get an ONNX model by exporting from various frameworks, see ONNX Tutorials.
If you already have an ONNX model, just install the runtime for your machine to try it out. One easy way to deploy the model on the cloud is by using Azure Machine Learning. See detailed instructions and sample notebooks.
Installation
APIs and Official Builds
| API Documentation | CPU package | GPU package* |
|---|---|---|
| Python** | Available on Pypi
|
Available on Pypi
|
| C# | Available on Nuget
|
Available on Nuget
|
| C | Available on Nuget
Files (.zip, .tgz)
|
Available on Nuget
Files (.zip, .tgz)
|
| C++ | Build from source | Build from source |
*Requires CUDA 9.1 and cuDNN 7.1
**Compatible with Python 3.5-3.7
System Requirements
- ONNX Runtime binaries in CPU packages use OpenMP and depends on the library being available at runtime in the
system.
- For Windows, OpenMP support comes as part of VC runtime. It is also available as redist packages: vc_redist.x64.exe and vc_redist.x86.exe
- For Linux, the system must have the libgomp.so.1 which can be installed using
apt-get install libgomp1.
- The GPU builds require the CUDA9.1 and cuDNN 7.3 runtime libraries being installed in the system.
Build Details
For details on the build configurations and information on how to create a build, see Build ONNX Runtime.
Versioning
See more details on API and ABI Versioning and ONNX Compatibility in Versioning.
Design and Key Features
For an overview of the high level architecture and key decisions in the technical design of ONNX Runtime, see Engineering Design.
ONNX Runtime is built with an extensible design that makes it versatile to support a wide array of models with high performance.
- Add a custom operator/kernel
- Add an execution provider
- Add a new graph transform
- Add a new rewrite rule
Contribute
We welcome your contributions! Please see the contribution guidelines.
Feedback
For any feedback or to report a bug, please file a GitHub Issue.
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.