"addmm_impl_cpu_" not implemented for 'Half'

[HazemKaroui]

I get the following error. Does anyone have any ideas what could be causing this? I cloned Kijai/flan-t5-xl-encoder-only-bf16 and installed the few requirements that were initially not found.

Error occurred when executing ELLATextEncode:

"addmm_impl_cpu_" not implemented for 'Half'

  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/execution.py", line 151, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/execution.py", line 81, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/execution.py", line 74, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/custom_nodes/ComfyUI_ELLA/ella.py", line 99, in encode
    cond = t5(text)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/custom_nodes/ComfyUI_ELLA/ella_model/model.py", line 268, in forward
    outputs = self.model(text_input_ids, attention_mask=attention_mask)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py", line 1980, in forward
    encoder_outputs = self.encoder(
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py", line 1115, in forward
    layer_outputs = layer_module(
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py", line 695, in forward
    self_attention_outputs = self.layer[0](
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py", line 602, in forward
    attention_output = self.SelfAttention(
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/transformers/models/t5/modeling_t5.py", line 521, in forward
    query_states = shape(self.q(hidden_states))  # (batch_size, n_heads, seq_length, dim_per_head)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/user/StabilityMatrix/Data/Packages/ComfyUI/venv/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 114, in forward
    return F.linear(input, self.weight, self.bias)

[FNSpd]

Try --fp32-text-enc

[quixot1c]

https://huggingface.co/Kijai/flan-t5-xl-encoder-only-bf16/tree/main works for me, it's smaller too. I did rename the folder to flan-t5-xl, which this node requires according to the README.

[HazemKaroui]

Try --fp32-text-enc

This solved it! Thank you. Works wonderfully