lllyasviel / lllyasviel/stable-diffusion-webui-forge

Torch 2.4 error (Your device does not support the current version of Torch; 4080 Super). So which devices DO support Torch 2.4?

Open
#988 38 comments 6 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

Fresh install from https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/download/latest/webui_forge_cu124_torch24.7z updated to latest commit 86ee2d9462cc3baf8618430513e2fc0b6e4cabff. Unable to run with "Your device does not support the current version of Torch/CUDA" error.

Using RTX 4080 Super, Windows 11, latest GeForce drivers, CUDA 12.4 installed from https://developer.nvidia.com/cuda-12-4-0-download-archive

If Torch 2.4 is not supported on this hardware, which devices does it support then? Or am I missing something? (Yes, I can probably roll back to https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/download/latest/webui_forge_cu121_torch21.7z, but I'd like to use the latest version of Torch).

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-223-g86ee2d94
Commit hash: 86ee2d9462cc3baf8618430513e2fc0b6e4cabff
Traceback (most recent call last):
File "C:\stable-diffusion\forge124\webui\launch.py", line 51, in
main()
File "C:\stable-diffusion\forge124\webui\launch.py", line 39, in main
prepare_environment()
File "C:\stable-diffusion\forge124\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:
https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/tag/latest
Press any key to continue . . .

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start in webui/modules/launch_utils.py at prepare_environment, called from webui/launch.py, and reproduce the packaged cu124_torch24 launch on Windows 11 with the RTX 4080 Super details provided. Trace the Torch/CUDA compatibility check and establish whether the reported hardware is incorrectly rejected or unsupported; a useful resolution should explain the supported devices or the relevant compatibility condition.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning, operating-systems
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.