Triton Inference Server Client /Engine/Plugins/NNE/NNERuntimeORT/Source/ThirdParty/Onnxruntime/ The software is part of the Onnxruntime library, which is used to run neural network inference through the onnx runtime backend and also to optimize ML models. https://github.com/triton-inference-server/server/blob/main/LICENSE Licencees P4 Git /Engine/Source/ThirdParty/Licenses