lllyasviel / lllyasviel/stable-diffusion-webui-forge
RuntimeError: Your device does not support the current version of Torch/CUDA! Consider download another version:
- Dominant language
- Python
- Stars
- 13k
- Forks
- 1.7k
- PR merge metrics
- No merged PRs in 30d
Description
Hi, any suggestions to fix this error?
I'm trying to install Stable Diffusion / Forge and not succeeding after many attempts installing / uninstalling / reinstalling.
"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: f2.0.1v1.10.1-previous-659-gc055f2d4
Commit hash: c055f2d43b07cbfd87ac3da4899a6d7ee52ebab9
Traceback (most recent call last):
File "D:\Program Files\Forge\webui\launch.py", line 54, in
main()
File "D:\Program Files\Forge\webui\launch.py", line 42, in main
prepare_environment()
File "D:\Program Files\Forge\webui\modules\launch_utils.py", line 434, in prepare_environment
raise RuntimeError(
RuntimeError: Your device does not support the current version of Torch/CUDA! Consider download another version:
MSVC v143 - VS 2022 C++ x64/x86 builds tools (latest)
Press any key to continue . . .
"
Am running Windows 10 Home, x64. OS Build 19045.5737
Processor AMD Ryzen 7 5800H with Radeon Graphics 3.20 GHz
Installed RAM 16.0 GB (15.4 GB usable)
Graphics Card NVIDIA GeForce RTX 3080 Laptop GPU (8 GB), AMD Radeon(TM) Graphics (497 MB)
Have tried the suggested solution here: https://github.com/lllyasviel/stable-diffusion-webui-forge/issues/988#issuecomment-2282715004 . Have tried uninstalling and reinstalling MSVC v143 - VS 2022 C++ x64/x86 builds tools (latest) and the rebooting.. but not working.
Have tried the one click, have tried via stability matrix, have tried previous version.. [webui_forge_cu121_torch21.7z] (uninstalling & rebooting between each).
Thank you,
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with modules/launch_utils.py at prepare_environment(), using the traceback from launch.py as the entry point. Review how the installation checks the available Torch/CUDA support against the reported Windows and GPU setup. Done would require a reproducible diagnosis and a clearly documented compatible installation path.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100