GPU isn't being utilized when running MDX models

[femfii]

My GPU stays idle at 1% and CPU use jumps to 100% when I run any MDX models.

[femfii]

Tried to install a new version of cuda and it made the problem even worse, now I can't run the GPU conversion at all.

Last Error Received:

Process: MDX-Net

If this error persists, please contact the developers with the error details.

Raw Error Details:

RuntimeError: "D:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:548 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/reference/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.
"
Traceback Error: "
  File "UVR.py", line 4716, in process_start
  File "separate.py", line 280, in seperate
  File "onnxruntime\capi\onnxruntime_inference_collection.py", line 335, in __init__
  File "onnxruntime\capi\onnxruntime_inference_collection.py", line 381, in _create_inference_session
"

Error Time Stamp [2023-08-17 19:48:55]

Full Application Settings:

vr_model: Choose Model
aggression_setting: 10
window_size: 512
batch_size: Default
crop_size: 256
is_tta: False
is_output_image: False
is_post_process: False
is_high_end_process: False
post_process_threshold: 0.2
vr_voc_inst_secondary_model: No Model Selected
vr_other_secondary_model: No Model Selected
vr_bass_secondary_model: No Model Selected
vr_drums_secondary_model: No Model Selected
vr_is_secondary_model_activate: False
vr_voc_inst_secondary_model_scale: 0.9
vr_other_secondary_model_scale: 0.7
vr_bass_secondary_model_scale: 0.5
vr_drums_secondary_model_scale: 0.5
demucs_model: Choose Model
segment: Default
overlap: 0.25
shifts: 2
chunks_demucs: Auto
margin_demucs: 44100
is_chunk_demucs: False
is_chunk_mdxnet: False
is_primary_stem_only_Demucs: False
is_secondary_stem_only_Demucs: False
is_split_mode: True
is_demucs_combine_stems: True
demucs_voc_inst_secondary_model: No Model Selected
demucs_other_secondary_model: No Model Selected
demucs_bass_secondary_model: No Model Selected
demucs_drums_secondary_model: No Model Selected
demucs_is_secondary_model_activate: False
demucs_voc_inst_secondary_model_scale: 0.9
demucs_other_secondary_model_scale: 0.7
demucs_bass_secondary_model_scale: 0.5
demucs_drums_secondary_model_scale: 0.5
demucs_pre_proc_model: No Model Selected
is_demucs_pre_proc_model_activate: False
is_demucs_pre_proc_model_inst_mix: False
mdx_net_model: UVR-MDX-NET Voc FT
chunks: Auto
margin: 44100
compensate: Auto
is_denoise: False
is_invert_spec: False
is_mixer_mode: False
mdx_batch_size: 2
mdx_voc_inst_secondary_model: No Model Selected
mdx_other_secondary_model: No Model Selected
mdx_bass_secondary_model: No Model Selected
mdx_drums_secondary_model: No Model Selected
mdx_is_secondary_model_activate: False
mdx_voc_inst_secondary_model_scale: 0.9
mdx_other_secondary_model_scale: 0.7
mdx_bass_secondary_model_scale: 0.5
mdx_drums_secondary_model_scale: 0.5
is_save_all_outputs_ensemble: True
is_append_ensemble_name: False
chosen_audio_tool: Manual Ensemble
choose_algorithm: Min Spec
time_stretch_rate: 2.0
pitch_rate: 2.0
is_gpu_conversion: True
is_primary_stem_only: False
is_secondary_stem_only: False
is_testing_audio: False
is_add_model_name: False
is_accept_any_input: False
is_task_complete: False
is_normalization: False
is_create_model_folder: False
mp3_bit_set: 320k
save_format: WAV
wav_type_set: PCM_16
help_hints_var: False
model_sample_mode: False
model_sample_mode_duration: 30
demucs_stems: All Stems

[femfii]

I solved this, took me long enough and I'm not sure which one of these steps was the correct one but here is basically everything I did:

I think the problem lied in a wrong CUDA version. You need to have cuda 11.6, check if your GPU is compatible here

1. Uninstall CUDA if you have it installed
2. Uninstall Ultimate Vocal Remover and be sure to delete the folder it lives in
3. Install CUDA version 11.6
4. Install cuDDN version 8.5.0.96 (Windows)
5. Install pytorch https://pytorch.org/get-started/locally/

6. reinstall ultimate vocal remover

   install CUDA https://developer.nvidia.com/cuda-downloads how to install cuddn https://docs.nvidia.com/deeplearning/cudnn/install-guide/index.html#installdriver-windows and when u copy the cuddn .dll files to the CUDA folder be sure to put the lib files in both the lib/x64 folder and the lib folder.

[dimadt]

I solved this, took me long enough and I'm not sure which one of these steps was the correct one but here is basically everything I did:

I think the problem lied in a wrong CUDA version. You need to have cuda 11.6, check if your GPU is compatible here

1. Uninstall CUDA if you have it installed
2. Uninstall Ultimate Vocal Remover and be sure to delete the folder it lives in
3. Install CUDA version 11.6
4. Install cuDDN version 8.5.0.96 (Windows)
5. Install pytorch https://pytorch.org/get-started/locally/
6. reinstall ultimate vocal remover

install CUDA https://developer.nvidia.com/cuda-downloads how to install cuddn https://docs.nvidia.com/deeplearning/cudnn/install-guide/index.html#installdriver-windows and when u copy the cuddn .dll files to the CUDA folder be sure to put the lib files in both the lib/x64 folder and the lib folder.

do you know, what if program will get cuda 12.2?