runtime error

Exit code: 1. Reason: e.cc:1099 CreateExecutionProviderFactoryInstance] Failed to create CUDAExecutionProvider. Require cuDNN 9.* and CUDA 12.*. Please install all dependencies as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported. Loading decoder... 2026-04-23 17:55:47.176690814 [E:onnxruntime:Default, provider_bridge_ort.cc:2369 TryGetProviderInfo_CUDA] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1962 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library /usr/local/lib/python3.13/site-packages/onnxruntime/capi/libonnxruntime_providers_cuda.so with error: libcublasLt.so.12: cannot open shared object file: No such file or directory  2026-04-23 17:55:47.176790351 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:1099 CreateExecutionProviderFactoryInstance] Failed to create CUDAExecutionProvider. Require cuDNN 9.* and CUDA 12.*. Please install all dependencies as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported. ✓ Using execution provider: Encoder=CPUExecutionProvider, Decoder=CPUExecutionProvider 2026-04-23 17:55:47,287 - __main__ - INFO - ✓ Text recognition model initialized 2026-04-23 17:55:47,288 - __main__ - ERROR - Failed to initialize HTR pipeline: Failed to initialize HTR pipeline components Traceback (most recent call last): File "/app/app.py", line 361, in <module> pipeline = HTRPipeline( segmentation_model_path=SEGMENTATION_MODEL_PATH, ...<9 lines>... segmentation_region_overlap_threshold = Config.SEGMENTATION_REGION_OVERLAP_THRESHOLD ) File "/app/app.py", line 156, in __init__ raise RuntimeError("Failed to initialize HTR pipeline components") RuntimeError: Failed to initialize HTR pipeline components

Container logs: