(.venv) ubuntuai@ubuntuai ~/dia (main)> CUDA_VISIBLE_DEVICES=1 python app.py --share
Using device: cuda
Loading Nari model...
/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:143: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.
  WeightNorm.apply(module, name, dim)
Launching Gradio interface...
* Running on local URL:  http://127.0.0.1:7862
* Running on public URL: https://xxxxx.gradio.live

This share link expires in 1 week. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)
Created temporary audio prompt file: /tmp/tmpkdcs_jm6.wav (orig sr: 48000)
Error during inference: Expected query, key, and value to have the same dtype, but got query.dtype: c10::BFloat16 key.dtype: float and value.dtype: float instead.
Traceback (most recent call last):
  File "/home/ubuntuai/dia/app.py", line 143, in run_inference
    output_audio_np = model.generate(
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/home/ubuntuai/dia/dia/model.py", line 374, in generate
    logits_Bx1xCxV, new_cache = decode_step(
  File "/home/ubuntuai/dia/dia/layers.py", line 743, in decode_step
    x, new_kv_cache = layer(
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/ubuntuai/dia/dia/layers.py", line 605, in forward
    sa_out, new_kv_cache = self.self_attention(
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/ubuntuai/dia/dia/layers.py", line 392, in forward
    attn_output = F.scaled_dot_product_attention(
RuntimeError: Expected query, key, and value to have the same dtype, but got query.dtype: c10::BFloat16 key.dtype: float and value.dtype: float instead.
Deleted temporary audio prompt file: /tmp/tmpkdcs_jm6.wav
Traceback (most recent call last):
  File "/home/ubuntuai/dia/app.py", line 143, in run_inference
    output_audio_np = model.generate(
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/home/ubuntuai/dia/dia/model.py", line 374, in generate
    logits_Bx1xCxV, new_cache = decode_step(
  File "/home/ubuntuai/dia/dia/layers.py", line 743, in decode_step
    x, new_kv_cache = layer(
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/ubuntuai/dia/dia/layers.py", line 605, in forward
    sa_out, new_kv_cache = self.self_attention(
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/ubuntuai/dia/dia/layers.py", line 392, in forward
    attn_output = F.scaled_dot_product_attention(
RuntimeError: Expected query, key, and value to have the same dtype, but got query.dtype: c10::BFloat16 key.dtype: float and value.dtype: float instead.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/gradio/queueing.py", line 625, in process_events
    response = await route_utils.call_process_api(
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/gradio/route_utils.py", line 322, in call_process_api
    output = await app.get_blocks().process_api(
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/gradio/blocks.py", line 2136, in process_api
    result = await self.call_function(
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/gradio/blocks.py", line 1662, in call_function
    prediction = await anyio.to_thread.run_sync(  # type: ignore
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2470, in run_sync_in_worker_thread
    return await future
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 967, in run
    result = context.run(func, *args)
  File "/home/ubuntuai/dia/.venv/lib/python3.10/site-packages/gradio/utils.py", line 883, in wrapper
    response = f(*args, **kwargs)
  File "/home/ubuntuai/dia/app.py", line 206, in run_inference
    raise gr.Error(f"Inference failed: {e}")
gradio.exceptions.Error: 'Inference failed: Expected query, key, and value to have the same dtype, but got query.dtype: c10::BFloat16 key.dtype: float and value.dtype: float instead.'