run wan2.2 text to image crash(RTX5090 + cuda12.8 + pytorch2.9 + python12.10)

### Custom Node Testing

- [ ] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

run wan2.2 text to image crash(RTX5090 + cuda12.8 + pytorch2.9 + python12.10)

### Actual Behavior

run wan2.2 text to image crash(RTX5090 + cuda12.8 + pytorch2.9 + python12.10)

### Steps to Reproduce

run wan2.2 text to image crash(RTX5090 + cuda12.8 + pytorch2.9 + python12.10)

### Debug Logs

```powershell
o see the GUI go to: http://0.0.0.0:8888
got prompt
Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Using scaled fp8: fp8 matrix mult: False, scale input: False
Requested to load WanTEModel
loaded completely 9.5367431640625e+25 6419.477203369141 True
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16
Using scaled fp8: fp8 matrix mult: True, scale input: True
model weight dtype torch.float8_e4m3fn, manual cast: torch.float16
model_type FLOW
Requested to load WAN21
loaded completely 21192.103538938947 13626.341049194336 True
100%|████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:13<00:00, 6.55s/it]

(.venv) D:\ComfyUI>python -c "import torch; print(torch.cuda.get_device_capability())"
(12, 0)

(.venv) D:\ComfyUI>
```

### Other

_No response_