RuntimeError on MacOs: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False.

[deadcat000]

Not able to make it run on my M1Max anymore. I am using the latest stable torch.

RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

grounding-dino is using models/bert-base-uncased
final text_encoder_type: /Users/nicola/ComfyUI/models/bert-base-uncased
using extra model: /Users/nicola/ComfyUI/models/sams/sam_hq_vit_h.pth
!!! Exception during processing !!! Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
Traceback (most recent call last):
File "/Users/nicola/ComfyUI/execution.py", line 323, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "/Users/nicola/ComfyUI/execution.py", line 198, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "/Users/nicola/ComfyUI/execution.py", line 169, in _map_node_over_list
process_inputs(input_dict, i)
File "/Users/nicola/ComfyUI/execution.py", line 158, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "/Users/nicola/ComfyUI/custom_nodes/comfyui_segment_anything/node.py", line 269, in main
sam_model = load_sam_model(model_name)
File "/Users/nicola/ComfyUI/custom_nodes/comfyui_segment_anything/node.py", line 86, in load_sam_model
sam = sam_model_registrymodel_type
File "/Users/nicola/ComfyUI/custom_nodes/comfyui_segment_anything/sam_hq/build_sam_hq.py", line 19, in build_sam_hq_vit_h
return _build_sam_hq(
File "/Users/nicola/ComfyUI/custom_nodes/comfyui_segment_anything/sam_hq/build_sam_hq.py", line 122, in _build_sam_hq
return _load_sam_checkpoint(sam, checkpoint)
File "/Users/nicola/ComfyUI/custom_nodes/comfyui_segment_anything/sam_hq/build_sam_hq.py", line 67, in _load_sam_checkpoint
state_dict = torch.load(f)
File "/Users/nicola/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/impact_subpack/impact/subcore.py", line 24, in torch_wrapper
return orig_torch_load(*args, **kwargs)
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/serialization.py", line 1465, in load
return _load(
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/serialization.py", line 1953, in _load
result = unpickler.load()
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/serialization.py", line 1917, in persistent_load
typed_storage = load_tensor(
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/serialization.py", line 1889, in load_tensor
wrap_storage=restore_location(storage, location),
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/serialization.py", line 686, in default_restore_location
result = fn(storage, location)
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/serialization.py", line 624, in _deserialize
device = _validate_device(location, backend_name)
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch/serialization.py", line 593, in _validate_device
raise RuntimeError(
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

[zhangjiabin1010]

same question