[Bug]: Rocm 5.x or 6.x . and which zluda version BEST VERSIONS FOR RX6600

[Geekyboi6117]

Checklist

• [x] 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
• [ ] The issue has not been reported before recently
• [x] The issue has been reported before but has not been fixed yet

What happened?

an you help me ? are you uing rocm 6.2 or 5.7 . is rocm environment detected mine says no using rocm home . are you using latest zluda? i have a rx 6600 and my generation speed are prety slow like 2its on some models and less then 2 on some .

LOG WHILE RUNNING

---

(venv) E:\AII\sd_AMD\stable-diffusion-webui-amdgpu>webui-user.bat venv "E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\venv\Scripts\Python.exe" WARNING: ZLUDA works best with SD.Next. Please consider migrating to SD.Next. Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)] Version: v1.10.1-amd-24-g63895a83 Commit hash: 63895a83f70651865cc9653583c69765009489f3 ROCm: agents=['gfx1032'] ROCm: version=5.7, using agent gfx1032 ZLUDA support: experimental Using ZLUDA in E:\AII\sd_AMD\stable-diffusion-webui-amdgpu.zluda No ROCm runtime is found, using ROCM_HOME='C:\Program Files\AMD\ROCm\5.7' E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\venv\lib\site-packages\timm\models\layers_init_.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {name} is deprecated, please import via timm.layers", FutureWarning) no module 'xformers'. Processing without... no module 'xformers'. Processing without... No module 'xformers'. Proceeding without it. E:\AII\sd_AMD\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 --disable-nan-check --opt-sdp-attention --medvram --no-half-vae --opt-split-attention --ckpt-dir 'E:\AII\Models' Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled ONNX failed to initialize: Failed to import diffusers.pipelines.pipeline_utils because of the following error (look up to see its traceback): Failed to import diffusers.models.autoencoders.autoencoder_kl because of the following error (look up to see its traceback): Failed to import diffusers.loaders.unet because of the following error (look up to see its traceback): cannot import name 'Cache' from 'transformers' (E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\venv\lib\site-packages\transformers_init_.py) Loading weights [9fdc4c813d] from E:\AII\Models\epicrealismXL_vxvAnewstoryRealism.safetensors Running on local URL: http://127.0.0.1:7860 Creating model from config: E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\repositories\generative-models\configs\inference\sd_xl_base.yaml E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\venv\lib\site-packages\huggingface_hub\file_download.py:795: 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(

To create a public link, set share=True in launch(). Startup time: 12.9s (prepare environment: 16.4s, initialize shared: 0.8s, load scripts: 0.4s, create ui: 0.6s, gradio launch: 1.0s).

---

WHY ROCM NOT FOUNDING IS IT CASUING SLOW PERFORMANCE ???

---

WEBUI-USER.BAT

@echo off set PYTHON= set GIT= set VENV_DIR= set COMMANDLINE_ARGS=--use-zluda --disable-nan-check --opt-sdp-attention --medvram --no-half-vae --opt-split-attention --ckpt-dir "E:\AII\Models" --precision full --no-half call webui.bat

Steps to reproduce the problem

1. RUN WEBUI-USER.BAT
2. says no rocm runtime detected using rocm home
3. well rocm 5.7 works with 3.5 zluda
4. but extremely slow speed like less 2its on some models . rx6600 isnt that bad i saw people with rx580 have that speed

What should have happened?

should have better speed . am i doing some thing wrong like should i use rocm 6.2 with latest zluda ?

What browsers do you use to access the UI ?

No response

Sysinfo

sysinfo-2025-03-08-15-14.json

Console logs

(venv) E:\AII\sd_AMD\stable-diffusion-webui-amdgpu>webui-user.bat
venv "E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\venv\Scripts\Python.exe"
WARNING: ZLUDA works best with SD.Next. Please consider migrating to SD.Next.
Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr  5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]
Version: v1.10.1-amd-24-g63895a83
Commit hash: 63895a83f70651865cc9653583c69765009489f3
ROCm: agents=['gfx1032']
ROCm: version=5.7, using agent gfx1032
ZLUDA support: experimental
Using ZLUDA in E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\.zluda
No ROCm runtime is found, using ROCM_HOME='C:\Program Files\AMD\ROCm\5.7'
E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\venv\lib\site-packages\timm\models\layers\__init__.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
  warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
E:\AII\sd_AMD\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 --disable-nan-check --opt-sdp-attention --medvram --no-half-vae --opt-split-attention --ckpt-dir 'E:\AII\Models' --precision full --no-half
Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled
ONNX failed to initialize: Failed to import diffusers.pipelines.pipeline_utils because of the following error (look up to see its traceback):
Failed to import diffusers.models.autoencoders.autoencoder_kl because of the following error (look up to see its traceback):
Failed to import diffusers.loaders.unet because of the following error (look up to see its traceback):
cannot import name 'Cache' from 'transformers' (E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\venv\lib\site-packages\transformers\__init__.py)
Loading weights [6ce0161689] from E:\AII\Models\v1-5-pruned-emaonly.safetensors
Creating model from config: E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\configs\v1-inference.yaml
E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\venv\lib\site-packages\huggingface_hub\file_download.py:795: 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: 11.3s (prepare environment: 14.5s, initialize shared: 0.7s, load scripts: 0.4s, create ui: 0.4s, gradio launch: 0.7s).
Applying attention optimization: Doggettx... done.
Model loaded in 2.3s (load weights from disk: 0.3s, create model: 0.6s, apply weights to model: 1.1s, hijack: 0.1s, calculate empty prompt: 0.1s).

txt2img: CAT
E:\AII\sd_AMD\stable-diffusion-webui-amdgpu\modules\safe.py:156: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  return unsafe_torch_load(filename, *args, **kwargs)
 25%|███████████████████████████████████████████▌                                                                                                                                  | 5/20 [00:36<01:50,  7.35s/it]Interrupted with signal 2 in <frame at 0x000001AAC8819F70, file 'C:\\Users\\ABDULLAH\\AppData\\Local\\Programs\\Python\\Python310\\lib\\threading.py', line 324, code wait>         | 5/20 [00:29<01:37,  6.48s/it]
Terminate batch job (Y/N)? Y

Additional information

No response

[CS1o]

Hey, you should use ROCm HIP SDK 6.2.4 with your GPU. You also used the wrong launch args. only use --use-zluda --skip-ort --medvram-sdxl

Better reinstall it following my install Guide from here: https://github.com/CS1o/Stable-Diffusion-Info/wiki/Webui-Installation-Guides

[Geekyboi6117]

Hey, you should use ROCm HIP SDK 6.2.4 with your GPU. You also used the wrong launch args. only use --use-zluda --skip-ort --medvram-sdxl

Better reinstall it following my install Guide from here: https://github.com/CS1o/Stable-Diffusion-Info/wiki/Webui-Installation-Guides

reinstalled with your method . btw instead of deleting rocm 5.7 . because it seems to work for comfyui-zluda . i just renamed it and changed enviroment vars to 6.2 . restarted installed with your step . again the console log says no rocm runtime found using rocm home . and its been 20+ mints for the first prompt . but still it says compilation in progress .why is that? i remember when i used comfyui . with no cammanline args in it . it just runs under 30 sec for the first prompt . but speed is just under 2 its . which is still better then my r5 5600 speed . idn what is happening . can you anydesk and check?

[Geekyboi6117]

Hey, you should use ROCm HIP SDK 6.2.4 with your GPU. You also used the wrong launch args. only use --use-zluda --skip-ort --medvram-sdxl

Better reinstall it following my install Guide from here: https://github.com/CS1o/Stable-Diffusion-Info/wiki/Webui-Installation-Guides

here is the console log till this message

Failed to create model quickly; will retry using slow method. Compilation is in progress. Please wait... Applying attention optimization: Doggettx... done. Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Model loaded in 623.3s (calculate hash: 2.3s, create model: 2.0s, apply weights to model: 20.4s, move model to device: 0.1s, load textual inversion embeddings: 113.9s, calculate empty prompt: 484.3s). Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... 0%| | 0/20 [00:00<?, ?it/s]Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait... Compilation is in progress. Please wait..

---

[Geekyboi6117]

Hey, you should use ROCm HIP SDK 6.2.4 with your GPU. You also used the wrong launch args. only use --use-zluda --skip-ort --medvram-sdxl

Better reinstall it following my install Guide from here: https://github.com/CS1o/Stable-Diffusion-Info/wiki/Webui-Installation-Guides

---

check #588 for more info

[CS1o]

The message "no rocm runtime found, will be using ROCm at C:\Programms..." is normal and can be ignored if it points to the correct path.

The Compiling is normal and should only appear two times. First when installing and launching the webui. Second time when generating the first image. After that the zluda compiled file is stored and only needs a recompile if torch or driver changes.

Please don't split this into two problems for the same issue and close your other issue. You can add me on Discord (same Name as here) and I can check later what's going on.

[Geekyboi6117]

The message "no rocm runtime found, will be using ROCm at C:\Programms..." is normal and can be ignored if it points to the correct path.

The Compiling is normal and should only appear two times. First when installing and launching the webui. Second time when generating the first image. After that the zluda compiled file is stored and only needs a recompile if torch or driver changes.

Please don't split this into two problems for the same issue and close your other issue. You can add me on Discord (same Name as here) and I can check later what's going on.

req send . sorry but bro i am too much tired watched like 20 tuts downloaded 100+ gb files . still slow gen speed . i thought zluda will help .... i will dm and when you are free i can anydesk ... please fix it