Media generation failed: NVML_SUCCESS == r INTERNAL ASSERT FAILED at “/opt/pytorch/c10/cuda/CUDACachingAllocator.cpp”:1015, please report a bug to PyTorch.
PyTorch版本： 2.6.0，L4T:36.4.7
Hi,
Could you share the complete log so we can know more about the issue?
Thanks.
loaded partially; 2854.85 MB usable, 2721.74 MB loaded, 2696.00 MB offloaded, 120.00 MB buffer reserved, lowvram patches: 0
!!! Exception during processing !!! NVML_SUCCESS == r INTERNAL ASSERT FAILED at “/opt/pytorch/c10/cuda/CUDACachingAllocator.cpp”:1015, please report a bug to PyTorch.
Traceback (most recent call last):
File “/opt/ComfyUI/execution.py”, line 515, 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 “/opt/ComfyUI/execution.py”, line 329, 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 “/opt/ComfyUI/execution.py”, line 303, in _async_map_node_over_list
await process_inputs(input_dict, i)
File “/opt/ComfyUI/execution.py”, line 291, in process_inputs
result = f(**inputs)
File “/opt/ComfyUI/nodes.py”, line 77, in encode
return (clip.encode_from_tokens_scheduled(tokens), )
File “/opt/ComfyUI/comfy/sd.py”, line 181, in encode_from_tokens_scheduled
pooled_dict = self.encode_from_tokens(tokens, return_pooled=return_pooled, return_dict=True)
File “/opt/ComfyUI/comfy/sd.py”, line 245, in encode_from_tokens
o = self.cond_stage_model.encode_token_weights(tokens)
File “/opt/ComfyUI/comfy/sd1_clip.py”, line 714, in encode_token_weights
out = getattr(self, self.clip).encode_token_weights(token_weight_pairs)
File “/opt/ComfyUI/comfy/sd1_clip.py”, line 45, in encode_token_weights
o = self.encode(to_encode)
File “/opt/ComfyUI/comfy/sd1_clip.py”, line 309, in encode
return self(tokens)
File “/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py”, line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File “/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py”, line 1750, in _call_impl
return forward_call(*args, **kwargs)
File “/opt/ComfyUI/comfy/sd1_clip.py”, line 269, in forward
embeds, attention_mask, num_tokens, embeds_info = self.process_tokens(tokens, device)
File “/opt/ComfyUI/comfy/sd1_clip.py”, line 216, in process_tokens
tokens_embed = self.transformer.get_input_embeddings()(tokens_embed, out_dtype=torch.float32)
File “/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py”, line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File “/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py”, line 1750, in _call_impl
return forward_call(*args, **kwargs)
File “/opt/ComfyUI/comfy/ops.py”, line 364, in forward
return self.forward_comfy_cast_weights(*args, **kwargs)
File “/opt/ComfyUI/comfy/ops.py”, line 355, in forward_comfy_cast_weights
weight, bias, offload_stream = cast_bias_weight(self, device=input.device, dtype=out_dtype, offloadable=True)
File “/opt/ComfyUI/comfy/ops.py”, line 124, in cast_bias_weight
weight = weight.to(dtype=dtype)
RuntimeError: NVML_SUCCESS == r INTERNAL ASSERT FAILED at “/opt/pytorch/c10/cuda/CUDACachingAllocator.cpp”:1015, please report a bug to PyTorch.
日志记录，谢谢解答
Hi,
Sorry for the late update.
According to your log, the error occurs from the NVML, but the tool is not available on the Jetson Orin.
Please refer to the document below for using ComfyUI on the Orin:
Thanks.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.