RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'

[likeatingcake]

RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'

[maxin-cn]

`(latte) yueyc@super-AS-4124GS-TNR:~/Latte$ bash sample/ffs.sh /home/yueyc/anaconda3/envs/latte/lib/python3.12/site-packages/diffusers/utils/outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. torch.utils._pytree._register_pytree_node( Using Ema! WARNING: using half percision for inferencing! 0%| | 0/250 [00:00<?, ?it/s] Traceback (most recent call last): File "/home/yueyc/Latte/sample/sample.py", line 141, in main(omega_conf) File "/home/yueyc/Latte/sample/sample.py", line 108, in main samples = diffusion.p_sample_loop( ^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/diffusion/gaussian_diffusion.py", line 454, in p_sample_loop for sample in self.p_sample_loop_progressive( File "/home/yueyc/Latte/diffusion/gaussian_diffusion.py", line 505, in p_sample_loop_progressive out = self.p_sample( ^^^^^^^^^^^^^^ File "/home/yueyc/Latte/diffusion/gaussian_diffusion.py", line 406, in p_sample out = self.p_mean_variance( ^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/diffusion/respace.py", line 92, in p_mean_variance return super().p_mean_variance(self._wrap_model(model), *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/diffusion/gaussian_diffusion.py", line 279, in p_mean_variance model_output = model(x, t, **model_kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/diffusion/respace.py", line 130, in call return self.model(x, new_ts, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/models/latte.py", line 352, in forward x = spatial_block(x, c) ^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/Latte/models/latte.py", line 179, in forward x = x + gate_msa.unsqueeze(1) * self.attn(modulate(self.norm1(x), shift_msa, scale_msa)) ^^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.12/site-packages/torch/nn/modules/normalization.py", line 201, in forward return F.layer_norm( ^^^^^^^^^^^^^ File "/home/yueyc/anaconda3/envs/latte/lib/python3.12/site-packages/torch/nn/functional.py", line 2546, in layer_norm return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'

为何会出现这样的报错呢，求解答

Please refer to #38.

[github-actions]

Hi There! 👋

This issue has been marked as stale due to inactivity for 60 days.

We would like to inquire if you still have the same problem or if it has been resolved.

If you need further assistance, please feel free to respond to this comment within the next 7 days. Otherwise, the issue will be automatically closed.

We appreciate your understanding and would like to express our gratitude for your contribution to Latte. Thank you for your support. 🙏