Hi, I follow this instruction to update cuda & tensorrt version, but encounter failure.
here is the error log
in the last step installing tensorrt
nvidia@nvidia-desktop:~/tensorfiles$ sudo apt-get install tensorrt
Reading package lists... Done
Building dependency tree
Reading state information... Done
Some packages could not be installed. This may mean that you have
requested an impossible situation or if you are using the unstable
distribution that some required packages have not yet been created
or been moved out of Incoming.
The following information may help to resolve the situation:
The following packages have unmet dependencies:
tensorrt : Depends: python3-libnvinfer-dev (= 10.0.1.6-1+cuda12.4) but it is not going to be installed
E: Unable to correct problems, you have held broken packages.
Hi, I use trtexec compile a model in onnx to create an engine, but sometimes this command return success, in other times, failure occurs.
I’d like to know why this happens. I’m wondering whether the cuda & tensorrt configuration is valid or do I do something wrong?
I attached the onnx file. plz rename it with extension .onnx
[07/30/2024-17:55:34] [V] [TRT] CUDA lazy loading is enabled.
[07/30/2024-17:55:34] [I] Setting persistentCacheLimit to 0 bytes.
[07/30/2024-17:55:34] [I] Created execution context with device memory size: 0 MiB
[07/30/2024-17:55:34] [I] Using random values for input in
[07/30/2024-17:55:34] [I] Input binding for in with dimensions 1x3x3x3 is created.
[07/30/2024-17:55:34] [I] Output binding for out with dimensions 1x7x3x7 is created.
[07/30/2024-17:55:34] [I] Starting inference
Cuda failure: device not ready