Project Title

onnxruntime — Cross-platform, high performance ML inferencing and training accelerator

Overview

ONNX Runtime is a cross-platform inference and training machine-learning accelerator that enables faster customer experiences and lower costs. It supports models from various deep learning frameworks and classical machine learning libraries, and is compatible with different hardware, drivers, and operating systems. ONNX Runtime leverages hardware accelerators where applicable alongside graph optimizations and transforms to provide optimal performance.

Key Features

Cross-platform inference and training support
Compatibility with multiple deep learning frameworks and classical machine learning libraries
Hardware accelerator support and graph optimizations for optimal performance

Use Cases

Accelerating model training time on multi-node NVIDIA GPUs for transformer models
Enabling faster customer experiences and lower costs by supporting models from various frameworks
Leveraging hardware accelerators to optimize performance across different hardware, drivers, and operating systems

Advantages

Supports a wide range of deep learning frameworks and classical machine learning libraries
Optimizes performance by leveraging hardware accelerators and graph optimizations
Compatible with different hardware, drivers, and operating systems

Limitations / Considerations

Windows distributions may collect usage data and send it to Microsoft
May require additional setup and configuration for specific hardware accelerators

TensorFlow: A popular open-source machine learning framework that also supports model training and inference. ONNX Runtime differs in its focus on cross-platform inference and training acceleration.
PyTorch: Another widely-used open-source machine learning framework. ONNX Runtime supports PyTorch models, but is not a framework itself.
OpenVINO Toolkit: An open-source toolkit for optimizing and deploying AI models on Intel hardware. ONNX Runtime is more focused on cross-platform support and not limited to a specific hardware vendor.

Basic Information

GitHub: https://github.com/microsoft/onnxruntime
Stars: 17,578
License: MIT
Last Commit: 2025-08-20

📊 Project Information

Project Name: onnxruntime
GitHub URL: https://github.com/microsoft/onnxruntime
Programming Language: C++
⭐ Stars: 17,578
🍴 Forks: 3,406
📅 Created: 2018-11-10
🔄 Last Updated: 2025-08-20

🏷️ Project Topics

Topics: [, ", a, i, -, f, r, a, m, e, w, o, r, k, ", ,, , ", d, e, e, p, -, l, e, a, r, n, i, n, g, ", ,, , ", h, a, r, d, w, a, r, e, -, a, c, c, e, l, e, r, a, t, i, o, n, ", ,, , ", m, a, c, h, i, n, e, -, l, e, a, r, n, i, n, g, ", ,, , ", n, e, u, r, a, l, -, n, e, t, w, o, r, k, s, ", ,, , ", o, n, n, x, ", ,, , ", p, y, t, o, r, c, h, ", ,, , ", s, c, i, k, i, t, -, l, e, a, r, n, ", ,, , ", t, e, n, s, o, r, f, l, o, w, ", ]

📚 Documentation

🎥 Video Tutorials

youtube.com/@ONNXRuntime

This article is automatically generated by AI based on GitHub project information and README content analysis

onnxruntime

Project Description