Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]
Loading pipeline components...:  14%|█▍        | 1/7 [00:00<00:02,  2.53it/s]
Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00,  6.81it/s]`torch_dtype` is deprecated! Use `dtype` instead!


Loading checkpoint shards:   0%|          | 0/5 [00:00<?, ?it/s]

Loading checkpoint shards:  40%|████      | 2/5 [00:00<00:00, 18.13it/s]
Loading checkpoint shards: 100%|██████████| 5/5 [00:00<00:00, 34.83it/s]

Loading pipeline components...:  71%|███████▏  | 5/7 [00:00<00:00,  5.75it/s]The image processor of type `Qwen2VLImageProcessor` is now loaded as a fast processor by default, even if the model checkpoint was saved with a slow processor. This is a breaking change and may produce slightly different outputs. To continue using the slow processor, instantiate this class with `use_fast=False`. Note that this behavior will be extended to all models in a future release.

Loading pipeline components...: 100%|██████████| 7/7 [00:01<00:00,  4.27it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:01<00:00,  4.52it/s]

  0%|          | 0/50 [00:00<?, ?it/s]/fsx/sayak/miniconda3/envs/diffusers/lib/python3.10/site-packages/torch/nn/functional.py:2920: UserWarning: Mismatch dtype between input and weight: input dtype = float, weight dtype = c10::BFloat16, Cannot dispatch to fused implementation. (Triggered internally at /pytorch/aten/src/ATen/native/layer_norm.cpp:344.)
  return torch.rms_norm(input, normalized_shape, weight, eps)

  0%|          | 0/50 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "/fsx/sayak/diffusers/check_mag.py", line 22, in <module>
    output = pipe(
  File "/fsx/sayak/miniconda3/envs/diffusers/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
    return func(*args, **kwargs)
  File "/fsx/sayak/diffusers/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky.py", line 880, in __call__
    pred_velocity = self.transformer(
  File "/fsx/sayak/miniconda3/envs/diffusers/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/fsx/sayak/miniconda3/envs/diffusers/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
    return forward_call(*args, **kwargs)
  File "/fsx/sayak/diffusers/src/diffusers/models/transformers/transformer_kandinsky.py", line 659, in forward
    visual_embed = visual_transformer_block(
  File "/fsx/sayak/miniconda3/envs/diffusers/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1775, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/fsx/sayak/miniconda3/envs/diffusers/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1786, in _call_impl
    return forward_call(*args, **kwargs)
  File "/fsx/sayak/diffusers/src/diffusers/hooks/hooks.py", line 189, in new_forward
    output = function_reference.forward(*args, **kwargs)
  File "/fsx/sayak/diffusers/src/diffusers/hooks/mag_cache.py", line 186, in new_forward
    hidden_states = self._metadata._get_parameter_from_args_kwargs("hidden_states", args, kwargs)
  File "/fsx/sayak/diffusers/src/diffusers/hooks/_helpers.py", line 45, in _get_parameter_from_args_kwargs
    raise ValueError(f"Parameter '{identifier}' not found in function signature but was requested.")
ValueError: Parameter 'hidden_states' not found in function signature but was requested.