[Issue] Cannot Install with --Use-ZLUDA, Will Not Work #3785
Comments
|
For whatever it is worth, if anyone else hits this error, I did this to coerce SD.Next to operate with ZLuda. Open CMD/Terminal Once complete, exit this. Open Webui.bat with --Use-Zluda as the only parameter. The installer does not install the correct versions of pytorch. These steps got SD.Next operational on my setup. |
KhunDoug
changed the title
|
Zluda has up to 30 minutes of compile time for the first use. Getting stuck at the first start of generation is expected with Zluda. Can't really debug further as the rest of the logs are cut-off. |
|
The odd thing is that once I manullay upgrade/install a pytorch that has CUDA support, I get the Compiling messages. And it works well from there. But it refuses to install from scratch. And I can get it to go so far if I use –use-directml. But then that also crashes with an error that pytorch has no CUDA support.
Would it helpful if I temporarily renamed the SDNEXT folder and did another fresh install? That would grab the original error message.
From: Disty0 ***@***.***>
Sent: Tuesday, February 25, 2025 8:52 PM
To: vladmandic/sdnext ***@***.***>
Cc: KhunDoug ***@***.***>; Author ***@***.***>
Subject: Re: [vladmandic/sdnext] [Issue] Cannot Install with --Use-ZLUDA, Will Not Work (Issue #3785)
Zluda has up to 30 minutes of compile time for the first use. Getting stuck at the first start of generation is expected with Zluda.
Can't really debug further as the rest of the logs are cut-off.
—
Reply to this email directly, view it on GitHub<#3785 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AHEUDWV6ILT2SOPZBYLFIQT2RUM35AVCNFSM6AAAAABX3WWDYKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMOBTGY4TCOJVGI>.
You are receiving this because you authored the thread.Message ID: ***@***.******@***.***>>
[Disty0]Disty0 left a comment (vladmandic/sdnext#3785)<#3785 (comment)>
Zluda has up to 30 minutes of compile time for the first use. Getting stuck at the first start of generation is expected with Zluda.
Can't really debug further as the rest of the logs are cut-off.
—
Reply to this email directly, view it on GitHub<#3785 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AHEUDWV6ILT2SOPZBYLFIQT2RUM35AVCNFSM6AAAAABX3WWDYKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMOBTGY4TCOJVGI>.
You are receiving this because you authored the thread.Message ID: ***@***.******@***.***>>
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Issue Description
This is a clean install of SD.Next. The git pull works correctly and creates the SDNext folder inside my profile. I have Zluda installed and working correctly with Automatic1111 and ComfyUI.
The attempt to install with --use-zluda hit an error in the Python code and quits. I then tried to get things working with --use-directml. That gets as far as creating the VENV and looks correct. But then it bombs on an error that Torch is not compiled with CUDA support. At this point I tried using the --use-zluda and I get the webpage. I even have a model downloaded and installed. But trying to create a text to image just produces multiples instances of this:
16:44:00-269879 DEBUG Server: alive=True requests=459 memory=0/0 status='running' task='Load'
timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0
queued=0 uptime=1692 elapsed=1687.23 eta=None progress=0
I know Zluda and Python are working as I am able to ComfyUI and Automatic1111 and those work correctly, This error is isolated to SD.Next.
Version Platform Description
AMD Ryzen 5950X, XFX Radeon 6800XT, 64GB RAM, Windows 11 24H2
16:15:27-887166 INFO Starting SD.Next
16:15:27-891181 INFO Logger: file="C:\Users\Doug\sdnext\sdnext.log" level=DEBUG host="COLOSUSSUS5950AI" size=84
mode=create
16:15:27-893187 INFO Python: version=3.11.2 platform=Windows bin="C:\Users\Doug\sdnext\venv\Scripts\python.exe"
venv="C:\Users\Doug\sdnext\venv"
16:15:28-058593 INFO Version: app=sd.next updated=2025-02-24 hash=a1ab39bb branch=master
url=https://github.com/vladmandic/sdnext/tree/master ui=main
16:15:28-390275 INFO Platform: arch=AMD64 cpu=AMD64 Family 25 Model 33 Stepping 0, AuthenticAMD system=Windows
release=Windows-10-10.0.26100-SP0 python=3.11.2 locale=('English_United States', '1252')
docker=False
16:15:28-392281 DEBUG Packages: prefix=venv site=['venv', 'venv\Lib\site-packages']
16:15:28-392281 INFO Args: ['--use-zluda', '--debug']
16:15:28-394304 DEBUG Setting environment tuning
16:15:28-394304 DEBUG Torch allocator: "garbage_collection_threshold:0.80,max_split_size_mb:512"
16:15:28-398324 DEBUG Torch overrides: cuda=False rocm=False ipex=False directml=False openvino=False zluda=True
16:15:28-404354 INFO ROCm: AMD toolkit detected
16:15:28-776869 INFO ROCm: agents=['gfx1030']
16:15:28-776869 INFO ROCm: version=5.7, using agent gfx1030
16:15:28-778877 INFO Python: version=3.11.2 platform=Windows bin="C:\Users\Doug\sdnext\venv\Scripts\python.exe"
venv="C:\Users\Doug\sdnext\venv"
16:15:28-817119 INFO Using ZLUDA in C:\Users\Doug\sdnext.zluda
No ROCm runtime is found, using ROCM_HOME='C:\Program Files\AMD\ROCm\5.7'
16:15:30-482970 INFO Install: verifying requirements
16:15:30-529767 DEBUG Timestamp repository update time: Mon Feb 24 21:17:23 2025
16:15:30-531774 INFO Startup: standard
16:15:30-531774 INFO Verifying submodules
16:15:32-278719 DEBUG Git submodule: extensions-builtin/sd-extension-chainner / main
16:15:32-357121 DEBUG Git submodule: extensions-builtin/sd-extension-system-info / main
16:15:32-431777 DEBUG Git submodule: extensions-builtin/sd-webui-agent-scheduler / main
16:15:32-544431 DEBUG Git detached head detected: folder="extensions-builtin/sdnext-modernui" reattach=main
16:15:32-544431 DEBUG Git submodule: extensions-builtin/sdnext-modernui / main
16:15:32-618866 DEBUG Git submodule: extensions-builtin/stable-diffusion-webui-rembg / master
16:15:32-697250 DEBUG Git submodule: modules/k-diffusion / master
16:15:32-771618 DEBUG Git submodule: wiki / master
16:15:32-817874 DEBUG Register paths
16:15:32-880187 DEBUG Installed packages: 174
16:15:32-880187 DEBUG Extensions all: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
'sd-webui-agent-scheduler', 'sdnext-modernui', 'stable-diffusion-webui-rembg']
16:15:33-057813 DEBUG Extension installer:
C:\Users\Doug\sdnext\extensions-builtin\sd-webui-agent-scheduler\install.py
16:15:35-529987 DEBUG Extension installer:
C:\Users\Doug\sdnext\extensions-builtin\stable-diffusion-webui-rembg\install.py
16:15:44-264654 DEBUG Extensions all: []
16:15:44-264654 INFO Extensions enabled: ['Lora', 'sd-extension-chainner', 'sd-extension-system-info',
'sd-webui-agent-scheduler', 'sdnext-modernui', 'stable-diffusion-webui-rembg']
16:15:44-266659 INFO Install: verifying requirements
16:15:44-266659 DEBUG Setup complete without errors: 1740518144
Relevant log output
16:17:11-519634 INFO Base: pipeline=StableDiffusionPipeline task=TEXT_2_IMAGE batch=1/1x1 set={'guidance_scale': 6, 'generator': 'cpu:[1035819445]', 'num_inference_steps': 20, 'eta': 1.0, 'guidance_rescale': 0.7, 'output_type': 'latent', 'width': 512, 'height': 512, 'parser': 'native', 'prompt': 'embeds'} Progress ?it/s 0% 0/20 00:00 ? Base16:17:59-780118 DEBUG Server: alive=True requests=149 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=131 elapsed=126.74 eta=None progress=0 16:19:59-819638 DEBUG Server: alive=True requests=173 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=251 elapsed=246.78 eta=None progress=0 16:21:59-858499 DEBUG Server: alive=True requests=197 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=371 elapsed=366.82 eta=None progress=0 16:23:59-898537 DEBUG Server: alive=True requests=221 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=491 elapsed=486.86 eta=None progress=0 16:25:59-937521 DEBUG Server: alive=True requests=245 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=611 elapsed=606.89 eta=None progress=0 16:27:59-971670 DEBUG Server: alive=True requests=269 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=731 elapsed=726.93 eta=None progress=0 16:30:00-010841 DEBUG Server: alive=True requests=292 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=851 elapsed=846.97 eta=None progress=0 16:32:00-047393 DEBUG Server: alive=True requests=316 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=971 elapsed=967.0 eta=None progress=0 16:34:00-083663 DEBUG Server: alive=True requests=340 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=1091 elapsed=1087.04 eta=None progress=0 16:36:00-119365 DEBUG Server: alive=True requests=364 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=1211 elapsed=1207.08 eta=None progress=0 16:38:00-160004 DEBUG Server: alive=True requests=388 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=1331 elapsed=1327.12 eta=None progress=0 16:40:00-198218 DEBUG Server: alive=True requests=412 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=1451 elapsed=1447.16 eta=None progress=0 16:42:00-231645 DEBUG Server: alive=True requests=436 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=1572 elapsed=1567.19 eta=None progress=0 16:44:00-269879 DEBUG Server: alive=True requests=459 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=1692 elapsed=1687.23 eta=None progress=0 16:46:00-308035 DEBUG Server: alive=True requests=483 memory=0/0 status='running' task='Load' timestamp='20250225161553' id='task(wu9kkj2maxn0d7i)' job=0 jobs=0 total=1 step=0 steps=0 queued=0 uptime=1812 elapsed=1807.27 eta=None progress=0Backend
Diffusers
UI
Standard
Branch
Master
Model
StableDiffusion 1.5
Acknowledgements
The text was updated successfully, but these errors were encountered: