CUDA error: no kernel image is available for execution on the device (at I:\build_nunchaku\automv2\nunchaku\src\kernels\misc_kernels.cu:281)

[wer2288]

got prompt
[2025-12-30 11:09:11.182] [info] Initializing QuantizedFluxModel on device 0
[2025-12-30 11:09:11.182] [info] Use FP16 model
[2025-12-30 11:09:11.182] [info] Layer offloading enabled
[2025-12-30 11:09:11.197] [info] Loading partial weights from pytorch
!!! Exception during processing !!! CUDA error: no kernel image is available for execution on the device (at I:\build_nunchaku\automv2\nunchaku\src\kernels\misc_kernels.cu:281)
Traceback (most recent call last):
File "D:\ComfyUI-aki-v2\ComfyUI\execution.py", line 516, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-aki-v2\ComfyUI\execution.py", line 330, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-aki-v2\ComfyUI\execution.py", line 304, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "D:\ComfyUI-aki-v2\ComfyUI\execution.py", line 292, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "D:\ComfyUI-aki-v2\ComfyUI\custom_nodes\ComfyUI-nunchaku\nodes\models\flux.py", line 254, in load_model
self.transformer, self.metadata = NunchakuFluxTransformer2dModel.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-aki-v2\python\Lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-aki-v2\python\Lib\site-packages\nunchaku\models\transformers\transformer_flux.py", line 605, in from_pretrained
m = load_quantized_module(
^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI-aki-v2\python\Lib\site-packages\nunchaku\models\transformers\transformer_flux.py", line 456, in load_quantized_module
m.loadDict(path_or_state_dict, True)
RuntimeError: CUDA error: no kernel image is available for execution on the device (at I:\build_nunchaku\automv2\nunchaku\src\kernels\misc_kernels.cu:281)

Prompt executed in 0.58 seconds

这是什么问题？不支持2060super显卡吗？

[wer2288]

换了另外一个.whl文件后又提示：
CUDA error: invalid configuration argument (at F:\SageAtt_SpargeApp\Nunchaku\src\kernels\misc_kernels.cu:281)