False error with --use-zluda in Linux

Checklist

[ ] The issue exists after disabling all extensions
[X] The issue exists on a clean installation of webui
[ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
[X] The issue exists in the current version of the webui
[X] The issue has not been reported before recently
[ ] The issue has been reported before but has not been fixed yet

What happened?

Xubuntu 22.04. Kernel downgraded to 5.19.0-50-generic - because DKMS from ROCm 5.5 will not build on kernels above 5.19. RX 580 2048SP.

I install ROCm, build torch and torchvision. Create venv, install it here. After start clean install stable-diffusion-webui-amdgpu. webui-user.sh changes: export COMMANDLINE_ARGS="--use-zluda --medvram --theme dark --precision autocast --skip-version-check --device-id 0"

Now in console log present string:

Failed to install ZLUDA: [Errno 2] No such file or directory: '/home/bleach/pytorch2.1.2/stable-diffusion-webui-amdgpu/.zluda/cublas.dll'
Using CPU-only torch

but during generation CPU prefrably not used, GPU did the trick.

Steps to reproduce the problem

Described above

What should have happened?

Described above

What browsers do you use to access the UI ?

Mozilla Firefox

Sysinfo

sysinfo-2024-06-10-23-56.json

Console logs

./webui.sh 

################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.
################################################################

################################################################
Running on bleach user
################################################################

################################################################
Repo already cloned, using it as install directory
################################################################

################################################################
python venv already activate or run without venv: /home/bleach/pytorch2.1.2/stable-diffusion-webui-amdgpu/venv
################################################################

################################################################
Launching launch.py...
################################################################
glibc version is 2.35
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
WARNING: ZLUDA works best with SD.Next. Please consider migrating to SD.Next.
Python 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]
Version: v1.9.3-amd-25-g73a4e8c0
Commit hash: 73a4e8c03c897e1af83909d7218fc6a092189eec
Failed to install ZLUDA: [Errno 2] No such file or directory: '/home/bleach/pytorch2.1.2/stable-diffusion-webui-amdgpu/.zluda/cublas.dll'
Using CPU-only torch
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
/home/bleach/pytorch2.1.2/stable-diffusion-webui-amdgpu/venv/lib/python3.10/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(
Launching Web UI with arguments: --use-zluda --medvram --theme dark --precision autocast --skip-version-check --device-id 0
/home/bleach/pytorch2.1.2/stable-diffusion-webui-amdgpu/venv/lib/python3.10/site-packages/diffusers/models/transformers/transformer_2d.py:34: FutureWarning: `Transformer2DModelOutput` is deprecated and will be removed in version 1.0.0. Importing `Transformer2DModelOutput` from `diffusers.models.transformer_2d` is deprecated and this will be removed in a future version. Please use `from diffusers.models.modeling_outputs import Transformer2DModelOutput`, instead.
  deprecate("Transformer2DModelOutput", "1.0.0", deprecation_message)
ONNX: version=1.18.0 provider=CUDAExecutionProvider, available=['AzureExecutionProvider', 'CPUExecutionProvider']
Loading weights [6ce0161689] from /home/bleach/pytorch2.1.2/stable-diffusion-webui-amdgpu/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Creating model from config: /home/bleach/pytorch2.1.2/stable-diffusion-webui-amdgpu/configs/v1-inference.yaml
/home/bleach/pytorch2.1.2/stable-diffusion-webui-amdgpu/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
  warnings.warn(
Startup time: 7.7s (prepare environment: 10.1s, initialize shared: 0.8s, load scripts: 0.5s, create ui: 0.3s, gradio launch: 1.0s).
Applying attention optimization: Doggettx... done.
Model loaded in 2.6s (load weights from disk: 0.5s, create model: 0.3s, apply weights to model: 1.0s, apply half(): 0.2s, apply dtype to VAE: 0.2s, calculate empty prompt: 0.3s).
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:29<00:00,  1.49s/it]
Total progress: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:30<00:00,  1.53s/it]
Total progress: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:30<00:00,  1.46s/it]

Additional information

No response

lshqqytiger / stable-diffusion-webui-amdgpu