ZLUDA | Reactor does work, however it says onnxruntime-gpu is missing and uses cpu instead of cuda

[jhmangamer]

First, confirm

• I have read the instruction carefully
• I have searched the existing issues
• I have updated the extension to the latest version

What happened?

Problem is a combination of lllyasviel/stable-diffusion-webui-forge#88 and #412.

Extension works fine, but always uses CPU instead of GPU, even if CUDA is selected in the settings. I noticed ReActor throwing the error message The 'onnxruntime-gpu' distribution was not found and is required by the application, PLEASE, RESTART the Server! I think those events may be connected and it's a bug, because ReActor also states the right CUDA Version and even says - ReActor - STATUS - Running v0.7.0-b7 on Device: CUDA

Steps to reproduce the problem

1. Use lshqqytiger/stable-diffusion-webui-directml fork
2. Use zluda
3. Install extension
4. Make sure CUDA is selected in extension settings

Sysinfo

All on newest version: Windows 11, Firefox, lshqqytiger/stable-diffusion-webui-directml fork, AMD Radeon 7900XTX

Relevant console log

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: 1.8.0-RC
Commit hash: 7071a4a7e42e7d5588f7c3eee44d411953419f8d
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
D:\Programme\a1111\stable-diffusion-webui-directml\venv\lib\site-packages\pytorch_lightning\utilities\distributed.py:258: LightningDeprecationWarning: `pytorch_lightning.utilities.distributed.rank_zero_only` has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from `pytorch_lightning.utilities` instead.
  rank_zero_deprecation(
Collecting onnxruntime-gpu
  Using cached onnxruntime_gpu-1.17.1-cp310-cp310-win_amd64.whl.metadata (4.4 kB)
Requirement already satisfied: coloredlogs in d:\programme\a1111\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (15.0.1)
Requirement already satisfied: flatbuffers in d:\programme\a1111\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (24.3.7)
Requirement already satisfied: numpy>=1.21.6 in d:\programme\a1111\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (1.26.2)
Requirement already satisfied: packaging in d:\programme\a1111\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (23.2)
Requirement already satisfied: protobuf in d:\programme\a1111\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (3.20.3)
Requirement already satisfied: sympy in d:\programme\a1111\stable-diffusion-webui-directml\venv\lib\site-packages (from onnxruntime-gpu) (1.12)
Requirement already satisfied: humanfriendly>=9.1 in d:\programme\a1111\stable-diffusion-webui-directml\venv\lib\site-packages (from coloredlogs->onnxruntime-gpu) (10.0)
Requirement already satisfied: mpmath>=0.19 in d:\programme\a1111\stable-diffusion-webui-directml\venv\lib\site-packages (from sympy->onnxruntime-gpu) (1.3.0)
Requirement already satisfied: pyreadline3 in d:\programme\a1111\stable-diffusion-webui-directml\venv\lib\site-packages (from humanfriendly>=9.1->coloredlogs->onnxruntime-gpu) (3.4.1)
Using cached onnxruntime_gpu-1.17.1-cp310-cp310-win_amd64.whl (148.6 MB)
Installing collected packages: onnxruntime-gpu
CUDA 11.8
Error: The 'onnxruntime-gpu' distribution was not found and is required by the application

        +---------------------------------+
        --- PLEASE, RESTART the Server! ---
        +---------------------------------+
Launching Web UI with arguments: --use-zluda
ONNX: selected=CUDAExecutionProvider, available=['AzureExecutionProvider', 'CPUExecutionProvider']
ControlNet preprocessor location: D:\Programme\a1111\stable-diffusion-webui-directml\extensions\sd-webui-controlnet\annotator\downloads
2024-04-04 14:02:03,837 - ControlNet - INFO - ControlNet v1.1.443
2024-04-04 14:02:03,912 - ControlNet - INFO - ControlNet v1.1.443
14:02:04 - ReActor - STATUS - Running v0.7.0-b7 on Device: CUDA
Loading weights [84d76a0328] from D:\Programme\a1111\stable-diffusion-webui-directml\models\Stable-diffusion\epicrealism_naturalSinRC1VAE.safetensors
Creating model from config: D:\Programme\a1111\stable-diffusion-webui-directml\configs\v1-inference.yaml
2024-04-04 14:02:04,711 - ControlNet - INFO - ControlNet UI callback registered.
Running on local URL:  http://127.0.0.1:7860

Additional information

No response

[jhmangamer]

image generation and every other extension do in fact use the GPU with cuda via zluda

[Gourieff]

It's unlikely that ORT-GPU will work with ZLUDA from the box

[thejohnd0e]

same
the extension worked good bit last time i god it