createExecutionContextWithoutDeviceMemory() may not work well when deserializing a engine file to engine.
TensorRT Version: 220.127.116.11
GPU Type: GeForce RTX 3080
Nvidia Driver Version: 461.40-desktop-win10-64bit-international-dch-whql
CUDA Version: 11.1
CUDNN Version: 8.0.5
Operating System + Version: Windows 10
Steps To Reproduce
Anything works well when i build a engine from onnx model file(this model is ok, works well before), and process inference;
- build a engine from onnx model file;
- serialize the engine to disk as binary file;
- deserialize this binary file to engine;
- mEngine->createExecutionContextWithoutDeviceMemory() crashed.