Crashes with no error when using zluda

[Markznm]

Crashes without error info when pressing create
I have RX 580 2048SP (Maybe rx470 because aliexpress sellers often use its chip in rx580 2048sp refabs)
Driver version 24.7.1 and ROCm 5.7.1
Log:

Microsoft Windows [Version 10.0.19045.2673]
(c) Корпорация Майкрософт (Microsoft Corporation). Все права защищены.

C:\SD-Zluda\stable-diffusion-webui-amdgpu>webui-user.bat
venv "C:\SD-Zluda\stable-diffusion-webui-amdgpu\venv\Scripts\Python.exe"
WARNING: ZLUDA works best with SD.Next. Please consider migrating to SD.Next.
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.10.1-amd-2-g395ce8dc
Commit hash: 395ce8dc2cb01282d48074a89a5e6cb3da4b59ab
Using ZLUDA in C:\SD-Zluda\stable-diffusion-webui-amdgpu\.zluda
Skipping onnxruntime installation.
You are up to date with the most recent release.
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
C:\SD-Zluda\stable-diffusion-webui-amdgpu\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(
Launching Web UI with arguments: --use-zluda --update-check --skip-ort
Loading weights [6ce0161689] from C:\SD-Zluda\stable-diffusion-webui-amdgpu\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
Creating model from config: C:\SD-Zluda\stable-diffusion-webui-amdgpu\configs\v1-inference.yaml
C:\SD-Zluda\stable-diffusion-webui-amdgpu\venv\lib\site-packages\huggingface_hub\file_download.py:1150: 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(
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 26.0s (prepare environment: 29.1s, initialize shared: 5.8s, other imports: 1.2s, load scripts: 1.3s, create ui: 1.6s, gradio launch: 0.7s).
Applying attention optimization: Doggettx... done.
Для продолжения нажмите любую клавишу . . .

I can give more info if needed

[lshqqytiger]

You can try troubleshooting by following TROUBLESHOOTING.md.

[Markznm]

You can try troubleshooting by following TROUBLESHOOTING.md.

Thank you! I will try

[CS1o]

This behaviour can be fixed by relaunching the webui and pressing Generate again. It will crash,
Then repeat this step 10-15 times. It trys to load stuff in the background and should succeed then after doing that a few times.
Then you should get a 0/0 in the progress bar.
When you get this, just wait 15-40 minutes for the first image to be generated.
After that its done i will generate faster.

[1635200412]

I am an RX580 graphics card. I encountered an issue while running a Python program using the Zluda DLL file.
Python version: 3.10.11, Torch version: 2.0.1cu118
When running some Python programs, there is a high probability that the program will exit without any log. I tried to set AMD_LOG_LEVEL=1 and encountered numerous errors:

Failed to create hostcall buffer
Kernel expects a hostcall buffer, but none found

I suspect this might be due to the fact that the RX580 does not have official support for ROCm. I am using a third-party compiled ROCm from this GitHub repository, which might have some functional issues.

Strangely, sometimes the program can run, but there are still numerous errors like "Failed to create hostcall buffer".

:1:C:\constructicon\builds\gfx\two\23.19\drivers\compute\clr\rocclr\device\pal\palvirtual.cpp:3785: 178735641487 us: [pid:5676  tid:0x289c] Failed to create hostcall buffer
:1:C:\constructicon\builds\gfx\two\23.19\drivers\compute\clr\rocclr\device\pal\palkernel.cpp:344 : 178735642006 us: [pid:5676  tid:0x289c] Kernel expects a hostcall buffer, but none found
:1:C:\constructicon\builds\gfx\two\23.19\drivers\compute\clr\rocclr\device\pal\palvirtual.cpp:3785: 178735642051 us: [pid:5676  tid:0x289c] Failed to create hostcall buffer
:1:C:\constructicon\builds\gfx\two\23.19\drivers\compute\clr\rocclr\device\pal\palkernel.cpp:344 : 178735642078 us: [pid:5676  tid:0x289c] Kernel expects a hostcall buffer, but none found

In the Windows Event Log Management, there will be a large number of error reports in the Application Log.

错误应用程序名称: python.exe，版本: 3.10.11150.1013，时间戳: 0x6462d4eb
错误模块名称: amdhip64.dll，版本: 10.0.3584.0，时间戳: 0x66bcf007
异常代码: 0xc0000005
错误偏移量: 0x00000000003a8d72
错误进程 ID: 0x5ac
错误应用程序启动时间: 0x01db5fa3d0b9e08e
错误应用程序路径: D:\github\MSST-WebU\msst\python.exe
错误模块路径: C:\Windows\SYSTEM32\amdhip64.dll
报告 ID: 04acf6a0-13f4-434a-8b43-369d07ab96a0
错误程序包全名: 
错误程序包相对应用程序 ID: