[calibrator.cu::cuCalibrator::absTensorMax::146]

[xiao-lin-hub]

[04/27/2024-11:58:49] [TRT] [E] 1: [calibrator.cu::cuCalibrator::absTensorMax::146] Error Code 1: Cuda Runtime (invalid resource handle)
[04/27/2024-11:58:49] [TRT] [E] 1: [calibrator.cu::cuCalibrator::absTensorMax::146] Error Code 1: Cuda Runtime (invalid resource handle)
[04/27/2024-11:58:49] [TRT] [E] 1: [calibrator.cu::cuCalibrator::absTensorMax::146] Error Code 1: Cuda Runtime (invalid resource handle)
[04/27/2024-11:58:49] [TRT] [E] 1: [reformatRunner.cpp::nvinfer1::rt::cuda::ReformatRunner::execute::613] Error Code 1: Cuda Runtime (invalid resource handle)
[04/27/2024-11:58:49] [TRT] [E] 3: [engine.cpp::nvinfer1::rt::Engine::~Engine::307] Error Code 3: API Usage Error (Parameter check failed at: engine.cpp::nvinfer1::rt::Engine::~Engine::307, condition: mObjectCounter.use_count() == 1. Destroying an engine object before destroying objects it created leads to undefined behavior.
)
[04/27/2024-11:58:49] [TRT] [E] 2: [calibrator.cpp::nvinfer1::builder::calibrateEngine::1181] Error Code 2: Internal Error (Assertion context->executeV2(&bindings[0]) failed. )

[zerollzeng]

[04/27/2024-11:58:49] [TRT] [E] 1: [calibrator.cu::cuCalibrator::absTensorMax::146] Error Code 1: Cuda Runtime (invalid resource handle)

Looks like cuda issue, does it reproduce in the TensorRT docker container?