Introduction

Welcome to the CUDA toolkit documentation base.

Here you will find all the instructions you need to install, configure and understand the toolkit.

The LabVIEW CUDA toolkit is the world’s first framework built on ONNX and ONNX Runtime.

• ONNX (Open Neural Network Exchange) is an open standard format that enables the description and exchange of AI models in an interoperable way across tools and platforms.
• ONNX Runtime is the official execution engine, optimized to deploy these models efficiently across a wide range of hardware and environments.

Our validation of functional operators was performed with the following versions:

• ONNX: 1.18.0

• ONNX Runtime: 1.23.0+cu125

To explore the list of supported functional operators, visit:
Graiphic ONNX Runtime – Execution Providers Tester, in the ops20 folder.