"replication_pad1d_cuda" not implemented for 'BFloat16'

### Custom Node Testing

- [x] I have tried disabling custom nodes, updating torch and more, 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

At VAEDecodeAudio I get this error:
"replication_pad1d_cuda" not implemented for 'BFloat16'

I have updated Comfyui to latest version. I have disabled custom nodes.

### Actual Behavior

Won't decode the audio output from the sampler.

### Steps to Reproduce

### Model Download

Download the following model and save it to the **ComfyUI/models/checkpoints** folder.
[ace_step_v1_3.5b.safetensors](https://huggingface.co/Comfy-Org/ACE-Step_ComfyUI_repackaged/blob/main/all_in_one/ace_step_v1_3.5b.safetensors)

Used the provided workflow in comfyui for Ace.

### Debug Logs

```powershell
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\Downloads\ComfyUI\python_embeded\Lib\site-packages\torch\nn\modules\conv.py", line 310, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Administrator\Downloads\ComfyUI\python_embeded\Lib\site-packages\torch\nn\modules\conv.py", line 303, in _conv_forward
return F.conv1d(F.pad(input, self._reversed_padding_repeated_twice, mode=self.padding_mode),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: "replication_pad1d_cuda" not implemented for 'BFloat16'
```

### Other

_No response_