microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
https://onnxruntime.ai
MIT License
14.13k stars 2.85k forks source link

[Inference & Training] My Onnxruntime isnt detecting cuda even after all paths are perfectly given with compatible softwares #22016

Open tamannashah18 opened 1 week ago

tamannashah18 commented 1 week ago

Describe the issue

024-09-06 15:00:41.0156984 [E:onnxruntime:Default, provider_bridge_ort.cc:1992 onnxruntime::TryGetProviderInfo_CUDA] D:\a_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1637 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "D:\EYIC\Git repo handwriting\Git repo handwriting\Handwriting _Analysis\venv\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

2024-09-06 15:00:41.0416597 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:965 onnxruntime::python::CreateExecutionProviderInstance] Failed to create CUDAExecutionProvider. Require cuDNN 9. and CUDA 12., and the latest MSVC runtime. 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. 2024-09-06 15:00:42.0969770 [E:onnxruntime:Default, provider_bridge_ort.cc:1992 onnxruntime::TryGetProviderInfo_CUDA] D:\a_work\1\s\onnxruntime\core\session\provider_bridge_ort.cc:1637 onnxruntime::ProviderLibrary::Get [ONNXRuntimeError] : 1 : FAIL : LoadLibrary failed with error 126 "" when trying to load "D:\EYIC\Git repo handwriting\Git repo handwriting\Handwriting _Analysis\venv\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"

2024-09-06 15:00:42.1120911 [W:onnxruntime:Default, onnxruntime_pybind_state.cc:965 onnxruntime::python::CreateExecutionProviderInstance] Failed to create CUDAExecutionProvider. Require cuDNN 9. and CUDA 12., and the latest MSVC runtime. 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. Monitoring directory: data/images

To reproduce

i want it to run on CUDA

Urgency

It is an urgent matter

ONNX Runtime Installation

Built from Source

ONNX Runtime Version or Commit ID

1.19.2

PyTorch Version

2.4

Execution Provider

Default CPU, CUDA

Execution Provider Library Version

cuda 12.4

### Tasks
- [ ] NVIDIA A4000
tianleiwu commented 1 week ago

See https://github.com/microsoft/onnxruntime/issues/22000#issuecomment-2332188659