onnxruntime/docs/install/index.md

title	has_children	nav_order
Install ORT	false	1

Install ONNX Runtime (ORT)

{: .no_toc }

See the installation matrix for recommended instructions for desired combinations of target operating system, hardware, accelerator, and language.

Details on OS versions, compilers, language versions, dependent libraries, etc can be found under Compatibility.

Contents

{: .no_toc }

• TOC placeholder {:toc}

Python Installs

Install ONNX Runtime (ORT)

{: .no_toc }

pip install onnxruntime

pip install onnxruntime-gpu

Install ONNX to export the model

{: .no_toc }

## ONNX is built into PyTorch
pip install torch

## tensorflow
pip install tf2onnx

## sklearn
pip install skl2onnx

C#/C/C++/WinML Installs

Install ONNX Runtime (ORT)

{: .no_toc }

# CPU 
dotnet add package Microsoft.ML.OnnxRuntime --version 1.8.1

# GPU
dotnet add package Microsoft.ML.OnnxRuntime.Gpu --version 1.8.1

# DirectML
dotnet add package Microsoft.ML.OnnxRuntime.DirectML --version 1.8.1

# WinML
dotnet add package Microsoft.AI.MachineLearning --version 1.8.1

JavaScript Installs

Web ORT (client)

{: .no_toc }

npm install onnxruntime-web

Node ORT (server)

{: .no_toc }

npm install onnxruntime-node

React Native ORT

{: .no_toc }

npm install onnxruntime-react-native

ORT Training package

pip install torch-ort
python -m torch_ort.configure

Note: This installs the default version of the torch-ort and onnxruntime-training packages that are mapped to specific versions of the CUDA libraries. Refer to the install options in ONNXRUNTIME.ai.

Add ORTModule in the train.py

   from torch_ort import ORTModule
   .
   .
   .
   model = ORTModule(model)

Note: the model where ORTModule is wrapped needs to be a derived from the torch.nn.Module class.

Inference install table for all languages

The table below lists the build variants available as officially supported packages. Others can be built from source from each release branch.

Requirements

{: .no_toc }

• All builds require the English language package with en_US.UTF-8 locale. On Linux, install language-pack-en package by running locale-gen en_US.UTF-8 and update-locale LANG=en_US.UTF-8

• Windows builds require Visual C++ 2019 runtime.

• Please note additional requirements and dependencies in the table below:

	Official build	Nightly build	Reqs
Python	If using pip, run pip install --upgrade pip prior to downloading.
	CPU: onnxruntime	ort-nightly (dev)
	GPU - CUDA: onnxruntime-gpu	ort-nightly-gpu (dev)	View
	OpenVINO: intel/onnxruntime - Intel managed		View
	TensorRT (Jetson): Jetson Zoo - NVIDIA managed
C#/C/C++	CPU: Microsoft.ML.OnnxRuntime	ort-nightly (dev)
	GPU - CUDA: Microsoft.ML.OnnxRuntime.Gpu	ort-nightly (dev)	View
	GPU - DirectML: Microsoft.ML.OnnxRuntime.DirectML	ort-nightly (dev)	View
WinML	Microsoft.AI.MachineLearning		View
Java	CPU: com.microsoft.onnxruntime:onnxruntime		View
	GPU - CUDA: com.microsoft.onnxruntime:onnxruntime_gpu		View
Android	com.microsoft.onnxruntime:onnxruntime-mobile		View
iOS (C/C++)	CocoaPods: onnxruntime-mobile-c		View
Objective-C	CocoaPods: onnxruntime-mobile-objc		View
React Native	onnxruntime-react-native		View
Node.js	onnxruntime-node		View
Web	onnxruntime-web		View

Note: Dev builds created from the master branch are available for testing newer changes between official releases. Please use these at your own risk. We strongly advise against deploying these to production workloads as support is limited for dev builds.

Training install table for all languages

ONNX Runtime Training packages are available for different versions of PyTorch, CUDA and ROCm versions.

The install command is:

pip3 install torch-ort [-f location]
python 3 -m torch_ort.configure

The location needs to be specified for any specific version other than the default combination. The location for the different configurations are below:

	Official build (location)	Nightly build (location)
PyTorch 1.8.1 (CUDA 10.2)	onnxruntime_stable_torch181.cu102	onnxruntime_nightly_torch181.cu102
PyTorch 1.8.1 (CUDA 11.1)	onnxruntime_stable_torch181.cu111	onnxruntime_nightly_torch181.cu111
PyTorch 1.9 (CUDA 10.2) Default	onnxruntime-training	onnxruntime_nightly_torch190.cu102
PyTorch 1.9 (CUDA 11.1)	onnxruntime_stable_torch190.cu111	onnxruntime_nightly_torch190.cu111
[Preview] PyTorch 1.8.1 (ROCm 4.2)	onnxruntime_stable_torch181.rocm42	onnxruntime_nightly_torch181.rocm42
[Preview] PyTorch 1.9 (ROCm 4.2)	onnxruntime_stable_torch190.rocm42	onnxruntime_nightly_torch190.rocm42