Error generating speech: VibeVoice generation failed: GenerationMixin._prepare_cache_for_generation() takes 6 positional arguments but 7 were given

### 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 the one properly

### Actual Behavior

Error generating speech: VibeVoice generation failed: GenerationMixin._prepare_cache_for_generation() takes 6 positional arguments but 7 were given

### Steps to Reproduce

tried to use the recent vibevoice model of microsoft and got struck, the transformer library version and comfy version are mismatching

### Debug Logs

```powershell
Error generating speech: VibeVoice generation failed: GenerationMixin._prepare_cache_for_generation() takes 6 positional arguments but 7 were given
```

### Other

_No response_