ONNX Runtime
Production-grade AI engine to speed up inferencing in your existing technology stack for cross platform deployment.
Seamless integration and optimal performance
Achieve seamless integration of ONNX Runtime in Qualcomm AI Hub with the optimum model performance on Qualcomm Hexagon NPUs.
Submit on AI Hub
To use ONNX Runtime when submitting your compile job to Qualcomm AI Hub, please specify ‑‑target_runtime onnx.
Accelerated cross‑platform machine learning
Visit ONNX Runtime