Traceback (most recent call last):
  File "/workspace/kohya_ss/train_network.py", line 783, in <module>
    train(args)
  File "/workspace/kohya_ss/train_network.py", line 610, in train
    noise_pred = unet(noisy_latents, timesteps, encoder_hidden_states).sample
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/accelerate/utils/operations.py", line 495, in __call__
    return convert_to_fp32(self.model_forward(*args, **kwargs))
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/amp/autocast_mode.py", line 12, in decorate_autocast
    return func(*args, **kwargs)
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/diffusers/models/unet_2d_condition.py", line 381, in forward
    sample, res_samples = downsample_block(
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/diffusers/models/unet_2d_blocks.py", line 612, in forward
    hidden_states = attn(hidden_states, encoder_hidden_states=encoder_hidden_states).sample
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/diffusers/models/attention.py", line 216, in forward
    hidden_states = block(hidden_states, context=encoder_hidden_states, timestep=timestep)
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/diffusers/models/attention.py", line 484, in forward
    hidden_states = self.attn1(norm_hidden_states) + hidden_states
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/workspace/kohya_ss/library/train_util.py", line 1846, in forward_xformers
    out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None)  # 最適なのを選んでくれる
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 192, in memory_efficient_attention
    return _memory_efficient_attention(
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 295, in _memory_efficient_attention
    return _fMHA.apply(
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 41, in forward
    out, op_ctx = _memory_efficient_attention_forward_requires_grad(
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 320, in _memory_efficient_attention_forward_requires_grad
    op = _dispatch_fw(inp)
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 94, in _dispatch_fw
    return _run_priority_list(
  File "/workspace/kohya_ss/venv/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 69, in _run_priority_list
    raise NotImplementedError(msg)
NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:
     query       : shape=(5, 8960, 8, 40) (torch.bfloat16)
     key         : shape=(5, 8960, 8, 40) (torch.bfloat16)
     value       : shape=(5, 8960, 8, 40) (torch.bfloat16)
     attn_bias   : <class 'NoneType'>
     p           : 0.0
`flshattF` is not supported because:
    xFormers wasn't build with CUDA support
    Operator wasn't built - see `python -m xformers.info` for more info
`tritonflashattF` is not supported because:
    xFormers wasn't build with CUDA support
    requires A100 GPU
`cutlassF` is not supported because:
    xFormers wasn't build with CUDA support
    Operator wasn't built - see `python -m xformers.info` for more info
`smallkF` is not supported because:
    xFormers wasn't build with CUDA support
    dtype=torch.bfloat16 (supported: {torch.float32})
    max(query.shape[-1] != value.shape[-1]) > 32
    Operator wasn't built - see `python -m xformers.info` for more info
    unsupported embed per head: 40