amperecomputingai/onnxruntime repository overview

⁠Ampere® optimized ONNXRT Docker images

Ampere® Altra®, with high performance Ampere Optimized Frameworks, offers the best-in-class Artificial Intelligence inference performance for standard frameworks including TensorFlow, PyTorch and ONNXRT. Ampere optimized ONNXRT inference acceleration engine is fully integrated with ONNXRT framework. ONNX models and software written with ONNXRT API can run as-is, without any modifications.

⁠Starting container

sudo docker run --privileged=true --name ort-aio --network host -it amperecomputingai/onnxruntime:latest

Please refer to the Ampere optimized ONNXRunTime documentation⁠ for additional details.

Check out Ampere Model Library⁠ and make sure to visit us at Ampere Solutions Portal⁠!

⁠Support

Please contact us at [email protected]⁠

⁠LEGAL NOTICE

By accessing, downloading or using this software and any required dependent software (the “Ampere AI Software”), you agree to the terms and conditions of the software license agreements for the Ampere AI Software, which may also include notices, disclaimers, or license terms for third party software included with the Ampere AI Software. Please refer to the Ampere AI Software EULA v1.6⁠ or other similarly-named text file for additional details.