microsoft/onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

C++22K stars4.2K forks+5 today

Topics

#deep-learning#onnx#neural-networks#machine-learning#ai-framework#hardware-acceleration#pytorch#tensorflow#scikit-learn

What it does

ONNX Runtime is a high-performance machine learning inference and training accelerator that supports multiple frameworks and hardware platforms, enabling faster model deployment and lower costs.

Star history

Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.

Tracking

Last trending: 2026-08-22

Creator kit

Hook

🚀 Speed up your machine learning models with ONNX Runtime! Cross-platform support & optimal performance for any model or hardware. #ONNXRuntime

Content angles

Create a tutorial on how to optimize TensorFlow/Keras models using ONNX Runtime.
Develop a comparison blog post between ONNX Runtime and other inference engines like TensorRT.
Host a webinar discussing the latest features in ONNX Runtime's training capabilities for multi-node GPU setups.

Who should care

AI researchers, data scientists, machine learning engineers looking to optimize model performance.