reconnnecting

我用的RTX PRO 500072G显存的，按道理应该够用。但是运行的时候，就出现：：,然后comfyui 页面就reconnnecting.
File "E:\ComfyUI_blackwell_test\ComfyUI\custom_nodes\ComfyUI_JoyAI_Echo\nodes.py", line 196 in load_model
File "E:\ComfyUI_blackwell_test\ComfyUI\execution.py", line 303 in process_inputs
File "E:\ComfyUI_blackwell_test\ComfyUI\execution.py", line 315 in _async_map_node_over_list
File "E:\ComfyUI_blackwell_test\ComfyUI\execution.py", line 341 in get_output_data
File "E:\ComfyUI_blackwell_test\ComfyUI\execution.py", line 542 in execute
File "E:\ComfyUI_blackwell_test\ComfyUI\execution.py", line 784 in execute_async
File "asyncio\events.py", line 88 in _run
File "asyncio\base_events.py", line 1986 in _run_once
File "asyncio\base_events.py", line 641 in run_forever
File "asyncio\windows_events.py", line 322 in run_forever
File "asyncio\base_events.py", line 674 in run_until_complete
File "asyncio\runners.py", line 118 in run
File "asyncio\runners.py", line 194 in run
File "E:\ComfyUI_blackwell_test\ComfyUI\execution.py", line 724 in execute
File "E:\ComfyUI_blackwell_test\ComfyUI\main.py", line 355 in prompt_worker
File "threading.py", line 1012 in run
File "threading.py", line 1075 in _bootstrap_inner
File "threading.py", line 1032 in _bootstrap
请按任意键继续. . .

我的版本是“pytorch version: 2.12.1+cu130”

Reproduce the failure with the reported RTX PRO 5000, PyTorch 2.12.1+cu130 environment and capture the missing exception text before the reconnecting state. Start at custom_nodes/ComfyUI_JoyAI_Echo/nodes.py line 196, then trace the call through execution.py; done means identifying the failure cause and confirming that the workflow no longer terminates with the reconnecting behavior.

Written by the indexing model from the issue text.