Not utilizing GPUs

[mr-darksoul]

Describe the bug
Not utilizing GPU Nvidia RTX4090 (cloud) hosted on Vast ai

Details
What OS are you using?

• Linux

Are you using a GPU?

• NVIDIA

nvidia-smi

Fri Jan 19 19:58:57 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 545.29.02 Driver Version: 545.29.02 CUDA Version: 12.3 |
|-----------------------------------------+----------------------+----------------------+
| 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 4090 On | 00000000:07:00.0 On | Off |
| 0% 51C P8 21W / 490W | 194MiB / 24564MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
+---------------------------------------------------------------------------------------+
Which version of roop unleashed are you using?
Latest and Greatest

[mr-darksoul]

this pops up after I hit start button:

Applied providers: ['CPUExecutionProvider'], with options: {'CPUExecutionProvider': {}}
inswapper-shape: [1, 3, 128, 128]
2024-01-19 20:33:24.173581287 [E:onnxruntime:Default, provider_bridge_ort.cc:1480 TryGetProviderInfo_CUDA] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1193 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library libonnxruntime_providers_cuda.so with error: libcufft.so.10: cannot open shared object file: No such file or directory

[C0untFloyd]

You should try a CUDA version smaller than 12 (I'm using 11.8) and be sure to set the provider to cuda in the settings tab. Perhaps your issue is also related to #400