ltx audio vae encoder error with --bf16-vae. Why now only fp32?

```
...
File "E:\env\v313\Lib\site-packages\torch\nn\modules\module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
File "E:\SD\ComfyUI_windows_portable\ComfyUI\comfy\ldm\lightricks\vae\causal_audio_autoencoder.py", line 160, in forward
return self.conv(x)
~~~~~~~~~^^^
File "E:\env\v313\Lib\site-packages\torch\nn\modules\module.py", line 1775, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "E:\env\v313\Lib\site-packages\torch\nn\modules\module.py", line 1786, in _call_impl
return forward_call(*args, **kwargs)
File "E:\SD\ComfyUI_windows_portable\ComfyUI\comfy\ops.py", line 428, in forward
return super().forward(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "E:\env\v313\Lib\site-packages\torch\nn\modules\conv.py", line 548, in forward
return self._conv_forward(input, self.weight, self.bias)
~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\env\v313\Lib\site-packages\torch\nn\modules\conv.py", line 543, in _conv_forward
return F.conv2d(
~~~~~~~~^
input, weight, bias, self.stride, self.padding, self.dilation, self.groups
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)
^
RuntimeError: Input type (float) and bias type (struct c10::BFloat16) should be the same

Prompt executed in 0.59 seconds
```

update this mornig