What happened
torch.cuda.get_arch_list() :
sm_50 sm_60 sm_61 sm_70 sm_75 sm_80 sm_86 sm_90
WARNING: NVIDIA GeForce RTX 4080 is compute capability sm_89, but this install's PyTorch only has kernels for sm_50 sm_60 sm_61 sm_70 sm_75 sm_80 sm_86 sm_90. Generation will fail or fall back to the CPU. Re-run webui.sh --install (Windows: .\webui.bat --install) to pick the wheel index that matches the card, or force one with --torch-index cu130 - cu128 if the driver predates CUDA 13.
What you expected
To run
What you thought would happen instead.
Wrong cuda install
Steps to reproduce
run webui.bat install
1.
2.
3.
Environment
with
- OS: Windows 11
- GPU and VRAM (e.g. RTX 4090, 24GB), or "no GPU / fal only": RTX 4080
- Model, if relevant (Z-Image, Krea 2 Turbo, Krea 2 RAW, a fal model):
- Inline Studio version: Latest
Logs or screenshots
What happened
torch.cuda.get_arch_list() :
sm_50 sm_60 sm_61 sm_70 sm_75 sm_80 sm_86 sm_90
WARNING: NVIDIA GeForce RTX 4080 is compute capability sm_89, but this install's PyTorch only has kernels for sm_50 sm_60 sm_61 sm_70 sm_75 sm_80 sm_86 sm_90. Generation will fail or fall back to the CPU. Re-run
webui.sh --install(Windows:.\webui.bat --install) to pick the wheel index that matches the card, or force one with--torch-index cu130-cu128if the driver predates CUDA 13.What you expected
To run
What you thought would happen instead.
Wrong cuda install
Steps to reproduce
run webui.bat install
1.
2.
3.
Environment
with
Logs or screenshots