model_management.load_models_gpu error

torch2.9cu130
```

File "M:\ComfyUI\312_cu128\ComfyUI\custom_nodes\ComfyUI-SAM3DObjects\nodes\utils\stages.py", line 1128, in run_stage2
comfy.model_management.load_models_gpu([slat_gen_patcher, slat_emb_patcher])
File "M:\ComfyUI\312_cu128\ComfyUI\comfy\model_management.py", line 755, in load_models_gpu
loaded_model.model_load(lowvram_model_memory, force_patch_weights=force_patch_weights)
File "M:\ComfyUI\312_cu128\ComfyUI\comfy\model_management.py", line 538, in model_load
self.model_use_more_vram(use_more_vram, force_patch_weights=force_patch_weights)
File "M:\ComfyUI\312_cu128\ComfyUI\comfy\model_management.py", line 568, in model_use_more_vram
return self.model.partially_load(self.device, extra_memory, force_patch_weights=force_patch_weights)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "M:\ComfyUI\312_cu128\ComfyUI\comfy\model_patcher.py", line 1040, in partially_load
self.detach()
File "M:\ComfyUI\312_cu128\ComfyUI\comfy\model_patcher.py", line 1052, in detach
self.unpatch_model(self.offload_device, unpatch_weights=unpatch_all)
File "M:\ComfyUI\312_cu128\ComfyUI\comfy\model_patcher.py", line 917, in unpatch_model
self.model.to(device_to)
File "M:\ComfyUI\312_cu128\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1371, in to
return self._apply(convert)
^^^^^^^^^^^^^^^^^^^^
File "M:\ComfyUI\312_cu128\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 930, in _apply
module._apply(fn)
File "M:\ComfyUI\312_cu128\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 930, in _apply
module._apply(fn)
File "M:\ComfyUI\312_cu128\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 930, in _apply
module._apply(fn)
[Previous line repeated 2 more times]
File "M:\ComfyUI\312_cu128\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 957, in _apply
param_applied = fn(param)
^^^^^^^^^
File "M:\ComfyUI\312_cu128\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1364, in convert
raise NotImplementedError(
NotImplementedError: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.
```