&&&& FAILED TensorRT.trtexec [TensorRT v8402] # tensorrt/bin/trtexec --onnx=/models/converted.onnx --saveEngine=engine.trt --useCudaGraph I solved the issue by adding '--workspace=2000'. It works for me now: sudo docker run --gpus all -it --rm -v ${PWD}/model_repository:/models...
Tensors and Dynamic neural networks in Python with strong GPU acceleration - Directly use empty strided in cudagraph copy · pytorch/pytorch@8390843