Two machines with very similar SW stack but different GPUs generate different folded model using the Polygraphy tool on the same model onnx input

AI & Data Science Deep Learning (Training & Inference) TensorRT
7

It looks like this is the issue:

This ORT build has [‘TensorrtExecutionProvider’, ‘CUDAExecutionProvider’, ‘CPUExecutionProvider’] enabled. Since ORT 1.9, you are required to explicitly set the providers parameter when instantiating InferenceSession. For example, onnxruntime.InferenceSession(…, providers=[‘TensorrtExecutionProvider’, ‘CUDAExecutionProvider’, ‘CPUExecutionProvider’], …)

Can you try either upgrading ONNX-GraphSurgeon to the latest version or downgrading ONNX-Runtime to something < 1.9.0 on Machine #2?