Docker libcublas.so error

General
1

I compiled a docker with
CUDA 12.4

+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.100                Driver Version: 550.100        CUDA Version: 12.4     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA GeForce RTX 3090        On  |   00000000:01:00.0 Off |                  N/A |
| 80%   25C    P0            104W /  350W |      13MiB /  24576MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
+-----------------------------------------------------------------------------------------+

cuDNN 8

#define CUDNN_MAJOR 8
#define CUDNN_MINOR 9
#define CUDNN_PATCHLEVEL 6
--
#define CUDNN_VERSION (CUDNN_MAJOR * 1000 + CUDNN_MINOR * 100 + CUDNN_PATCHLEVEL)

and I’m using onnxruntime-gpu==1.17.1 according to NVIDIA - CUDA | onnxruntime
But I keep getting this when I’m trying to run my script:

2024-10-24 13:36:23.876521467 [E:onnxruntime:Default, provider_bridge_ort.cc:1534 TryGetProviderInfo_TensorRT] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1209 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library libonnxruntime_providers_tensorrt.so with error: libcublas.so.11: cannot open shared object file: No such file or directory

*************** EP Error ***************
EP Error /onnxruntime_src/onnxruntime/python/onnxruntime_pybind_state.cc:456 void onnxruntime::python::RegisterTensorRTPluginsAsCustomOps(onnxruntime::python::PySessionOptions&, const ProviderOptions&) Please install TensorRT libraries as mentioned in the GPU requirements page, make sure they're in the PATH or LD_LIBRARY_PATH, and that your GPU is supported.
 when using ['TensorrtExecutionProvider']
Falling back to ['CPUExecutionProvider'] and retrying.
****************************************

And idk what to do about it - it works, but I want to run it using TensorrtExecutionProvider

Can you please suggest me how to fix it?

2

Please describe what you did exactly. I don’t think you actually compiled a “docker” (docker daemon) but probably ran a container or possibly built a Docker image.