A100 operation not supported

[xs315431]

I have encountered a similar problem. I encountered the following error while using Lmxyy1999/svdq-int4-flux.1-dev. I asked grok3 and it told me that a100 supports int4. I have updated all my related dependencies, but this error still occurs. Is this a hardware device issue?

error message GPU 0 (NVIDIA A100-PCIE-40GB) Memory: 40653.8125 MiB VRAM > 14GiB，disable CPU offload !!! Exception during processing !!! CUDA error: operation not supported (at C:\Users\muyang\Desktop\nunchaku-dev\nunchaku\csrc\utils.h:20) Traceback (most recent call last): File "D:\ComfyUI_Mie_V3.0\ComfyUI\execution.py", line 327, 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 "D:\ComfyUI_Mie_V3.0\ComfyUI\execution.py", line 202, 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 "D:\ComfyUI_Mie_V3.0\ComfyUI\execution.py", line 174, in _map_node_over_list process_inputs(input_dict, i) File "D:\ComfyUI_Mie_V3.0\ComfyUI\execution.py", line 163, in process_inputs results.append(getattr(obj, func)(**inputs)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_Mie_V3.0\ComfyUI\custom_nodes\ComfyUI-nunchaku\nodes\models\flux.py", line 300, in load_model self.transformer = NunchakuFluxTransformer2dModel.from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_Mie_V3.0\python_embeded\Lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_Mie_V3.0\python_embeded\Lib\site-packages\nunchaku\models\transformers\transformer_flux.py", line 298, in from_pretrained m = load_quantized_module( ^^^^^^^^^^^^^^^^^^^^^^ File "D:\ComfyUI_Mie_V3.0\python_embeded\Lib\site-packages\nunchaku\models\transformers\transformer_flux.py", line 227, in load_quantized_module cutils.disable_memory_auto_release() RuntimeError: CUDA error: operation not supported (at C:\Users\muyang\Desktop\nunchaku-dev\nunchaku\csrc\utils.h:20)

Prompt executed in 3.37 seconds