NVIDIA GeForce RTX 5070 Ti with CUDA capability sm_120 is not compatible with the current PyTorch installation.

Currently enabled native sdp backends: ['flash', 'math', 'mem_efficient', 'cudnn']
Xformers is not installed!
Flash Attn is not installed!
Sage Attn is not installed!
C:\Users\jonat\Downloads\framepack_cu126_torch26\framepack_cu126_torch26\system\python\lib\site-packages\torch\cuda\__init__.py:235: UserWarning:
NVIDIA GeForce RTX 5070 Ti with CUDA capability sm_120 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_50 sm_60 sm_61 sm_70 sm_75 sm_80 sm_86 sm_90.
If you want to use the NVIDIA GeForce RTX 5070 Ti GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/

warnings.warn(
Namespace(share=False, server='127.0.0.1', port=None, inbrowser=True)
Free VRAM 14.6845703125 GB
High-VRAM Mode: False
Downloading shards: 100%|██████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 2642.91it/s]
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 4.54it/s]
Fetching 3 files: 100%|██████████████████████████████████████████████████████████████████████████| 3/3 [00:00

Start with the reported PyTorch warning for the NVIDIA GeForce RTX 5070 Ti and compare the installed CUDA capabilities with the PyTorch installation instructions linked in the issue. Reproduce the launch and checkpoint-loading behavior, then verify that the reported GPU is supported and loading completes without the compatibility warning.

Written by the indexing model from the issue text.