Optimize and Accelerate Machine Learning Inferencing and Training

Speed up machine learning process

Built-in optimizations that deliver up to 17X faster inferencing and up to 1.4X faster training

Plug into your existing technology stack

Support for a variety of frameworks, operating systems and hardware platforms

Build using proven technology

Used in Office 365, Visual Studio and Bing, delivering half Trillion inferences every day

Get Started Easily

Platform

Platform list contains six items

Windows
Linux
Mac
Android
iOS
Web Browser (Preview)

API

API list contains eight items

Python
C++
C#
C
Java
JS
Obj-C
WinRT

Architecture

Architecture list contains four items

X64
X86
ARM64
ARM32

Hardware Acceleration

Hardware Acceleration list contains fourteen items

Default  CPU
CUDA
DirectML
oneDNN
OpenVINO
TensorRT
NNAPI
ACL (Preview)
ArmNN (Preview)
CoreML (Preview)
MIGraphX (Preview)
NUPHAR (Preview)
Rockchip NPU (Preview)
Vitis AI (Preview)

Installation Instructions

Please select a combination of resources

“We use ONNX Runtime to easily deploy thousands of open-source state-of-the-art models in the Hugging Face model hub and accelerate private models for customers of the Accelerated Inference API on CPU and GPU.”

– Morgan Funtowicz, Machine Learning Engineer, Hugging Face

“The ONNX Runtime API for Java enables Java developers and Oracle customers to seamlessly consume and execute ONNX machine-learning models, while taking advantage of the expressive power, high performance, and scalability of Java.”

– Stephen Green, Director of Machine Learning Research Group, Oracle

“With ONNX Runtime, Adobe Target got flexibility and standardization in one package: flexibility for our customers to train ML models in the frameworks of their choice, and standardization to robustly deploy those models at scale for fast inference, to deliver true, real-time personalized experiences.”

– Georgiana Copil, Senior Computer Scientist, Adobe

“With customers around the globe, we’re seeing increased interest in deploying more effective models to power pricing solutions via ONNX Runtime. ONNX Runtime’s performance has given us the confidence to use this solution with our customers with more extreme transaction volume requirements.”

– Jason Coverston, Product Director, Navitaire

“ONNX Runtime has vastly increased Vespa.ai’s capacity for evaluating large models, both in performance and model types we support.”

– Lester Solbakken, Principal Engineer, Vespa.ai, Verizon Media

“Using a common model and code base, the ONNX Runtime allows Peakspeed to easily flip between platforms to help our customers choose the most cost-effective solution based on their infrastructure and requirements.”

– Oscar Kramer, Chief Geospatial Scientist, Peakspeed

“The unique combination of ONNX Runtime and SAS Event Stream Processing changes the game for developers and systems integrators by supporting flexible pipelines and enabling them to target multiple hardware platforms for the same AI models without bundling and packaging changes. This is crucial considering the additional build and test effort saved on an ongoing basis.”

– Saurabh Mishra, Senior Manager, Product Management, Internet of Things, SAS

“We use ONNX Runtime to accelerate model training for a 300M+ parameters model that powers code autocompletion in Visual Studio IntelliCode.”

– Neel Sundaresan, Director SW Engineering, Data & AI, Developer Division, Microsoft

“At CERN in the ATLAS experiment, we have integrated the C++ API of ONNX Runtime into our software framework: Athena. We are currently performing inferences using ONNX models especially in the reconstruction of electrons and muons. We are benefiting from its C++ compatibility, platform*-to-ONNX converters (* Keras, TensorFlow, PyTorch, etc) and its thread safety.”

– ATLAS Experiment team, CERN (European Organization for Nuclear Research)

“We needed a runtime engine to handle the transition from data science land to a high-performance production runtime system. ONNX Runtime (ORT) simply ‘just worked’. Having no previous experience with ORT, I was able to easily convert my models, and had prototypes running inference in multiple languages within just a few hours. ORT will be my go-to runtime engine for the foreseeable future.”

– Bill McCrary, Application Architect, Samtec

News & Announcements​​

SAS and Microsoft collaborate to democratize the use of Deep Learning Models

Artificial Intelligence (AI) developers enjoy the flexibility of choosing a model training framework of their choice. This includes both open-source frameworks as well as vendor-specific ones. While this is great for innovation, it does introduce the challenge of operationalization across different hardware platforms...

Read more
ORT and SAS

Optimizing BERT model for Intel CPU Cores using ONNX runtime default execution provider

The performance improvements provided by ONNX Runtime powered by Intel® Deep Learning Boost: Vector Neural Network Instructions (Intel® DL Boost: VNNI) greatly improves performance of machine learning model execution for developers...

Read more
ORT and Intel AI

Accelerate and simplify Scikit-learn model inference with ONNX Runtime

Scikit-learn is one of the most useful libraries for general machine learning in Python. To minimize the cost of deployment and avoid discrepancies, deploying scikit-learn models to production usually leverages Docker containers and pickle, the object serialization module of the Python standard library...

Read more
SKL and ORT logos

ONNX Runtime scenario highlight: Vespa.ai integration

Since its open source debut two years ago, ONNX Runtime has seen strong growth with performance improvements, expanded platform and device compatibility, hardware accelerator support, an extension to training acceleration, and more...

Read more
Vespa logo

Resources​​

Hardware Ecosystem

“ONNX Runtime enables our customers to easily apply NVIDIA TensorRT’s powerful optimizations to machine learning models, irrespective of the training framework, and deploy across NVIDIA GPUs and edge devices.”

– Kari Ann Briski, Sr. Director, Accelerated Computing Software and AI Product, NVIDIA

“We are excited to support ONNX Runtime on the Intel® Distribution of OpenVINO™. This accelerates machine learning inference across Intel hardware and gives developers the flexibility to choose the combination of Intel hardware that best meets their needs from CPU to VPU or FPGA.”

– Jonathan Ballon, Vice President and General Manager, Intel Internet of Things Group

“With support for ONNX Runtime, our customers and developers can cross the boundaries of the model training framework, easily deploy ML models in Rockchip NPU powered devices.”

– Feng Chen, Senior Vice President, Rockchip

“Xilinx is excited that Microsoft has announced Vitis™ AI interoperability and runtime support for ONNX Runtime, enabling developers to deploy machine learning models for inference to FPGA IaaS such as Azure NP series VMs and Xilinx edge devices.”

– Sudip Nag, Corporate Vice President, Software & AI Products, Xilinx