Comfyui 0.3.14 make a pic with lumina 2.0 model got bug report

[kingsdom-sk]

Describe the issue

I used Comfyui 0.3.14 make a pic with lumina 2.0 model, got following bug message:
Starting server

To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: C:\Comfyui0.3\ComfyUI\custom_nodes\ComfyUI-Manager\extension-node-map.json [DONE]
got prompt
model weight dtype torch.bfloat16, manual cast: None
model_type FLOW
Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: xpu:0, offload device: cpu, dtype: torch.bfloat16
Requested to load LuminaTEModel_
loaded completely 9.5367431640625e+25 4986.46142578125 True
2025-02-08 23:28:30,319 - _logger.py - IPEX - INFO - Currently split master weight for xpu only support sgd
2025-02-08 23:28:30,329 - _logger.py - IPEX - INFO - Conv BatchNorm folding failed during the optimize process.
2025-02-08 23:28:30,336 - _logger.py - IPEX - INFO - Linear BatchNorm folding failed during the optimize process.
2025-02-08 23:28:30,336 - _logger.py - IPEX - WARNING - [NotSupported]failed to apply concat_linear on unet, please report bugs
CLIP/text encoder model load device: xpu:0, offload device: cpu, current: xpu:0, dtype: torch.float16
2025-02-08 23:28:41,599 - _logger.py - IPEX - INFO - Currently split master weight for xpu only support sgd
2025-02-08 23:28:41,607 - _logger.py - IPEX - INFO - Conv BatchNorm folding failed during the optimize process.
2025-02-08 23:28:41,614 - _logger.py - IPEX - INFO - Linear BatchNorm folding failed during the optimize process.
2025-02-08 23:28:41,614 - _logger.py - IPEX - WARNING - [NotSupported]failed to apply concat_linear on unet, please report bugs
2025-02-08 23:28:42,841 - _logger.py - IPEX - INFO - Currently split master weight for xpu only support sgd
2025-02-08 23:28:42,848 - _logger.py - IPEX - INFO - Conv BatchNorm folding failed during the optimize process.
2025-02-08 23:28:42,855 - _logger.py - IPEX - INFO - Linear BatchNorm folding failed during the optimize process.
2025-02-08 23:28:42,856 - _logger.py - IPEX - WARNING - [NotSupported]failed to apply concat_linear on unet, please report bugs
Requested to load Lumina2
loaded completely 9524.21650390625 4977.7440185546875 True
2025-02-08 23:28:44,421 - _logger.py - IPEX - INFO - Currently split master weight for xpu only support sgd
2025-02-08 23:28:44,427 - _logger.py - IPEX - INFO - Conv BatchNorm folding failed during the optimize process.
2025-02-08 23:28:44,433 - _logger.py - IPEX - INFO - Linear BatchNorm folding failed during the optimize process.
2025-02-08 23:28:44,434 - _logger.py - IPEX - WARNING - [NotSupported]failed to apply concat_linear on unet, please report bugs
100%|██████████████████████████████████████████████████████████████████████████████████| 25/25 [06:08<00:00, 14.72s/it]
Requested to load AutoencodingEngine
loaded completely 2385.8601562500003 159.87335777282715 True
2025-02-08 23:34:52,809 - _logger.py - IPEX - INFO - Currently split master weight for xpu only support sgd
2025-02-08 23:34:52,825 - _logger.py - IPEX - INFO - Conv BatchNorm folding failed during the optimize process.
2025-02-08 23:34:52,832 - _logger.py - IPEX - INFO - Linear BatchNorm folding failed during the optimize process.
2025-02-08 23:34:52,833 - _logger.py - IPEX - WARNING - [NotSupported]failed to apply concat_linear on unet, please report bugs
Prompt executed in 385.98 seconds

lumina 2.0 is here:
https://github.com/[Alpha-VLLM/Lumina-Image-2.0](https://github.com/Alpha-VLLM/Lumina-Image-2.0)

[simonlui]

Those messages are superfluous or are warnings about some optimizations not taking effect with IPEX. You should still get an output that is coherent so that shouldn't be a worry.

[kingsdom-sk]

OK

[huiyan2021]

@kingsdom-sk Could this issue be closed?