CUDA error: no kernel image is available for execution on the device Search for ...
🚨 错误信息
torch.AcceleratorError: CUDA error: no kernel image is available for execution on the device
Search for `cudaErrorNoKernelImageForDevice' in https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html for more information.
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
File "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 525, 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 "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 334, 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 "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 308, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "E:\ComfyUI_windows_portable\ComfyUI\execution.py", line 296, in process_inputs
result = f(**inputs)
File "E:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 80, in encode
return (clip.encode_from_tokens_scheduled(tokens), )
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 313, in encode_from_tokens_scheduled
pooled_dict = self.encode_from_tokens(tokens, return_pooled=return_pooled, return_dict=True)
File "E:\ComfyUI_windows_portable\ComfyUI\comfy\sd.py", line 377, in encode_from_tokens
o = self.cond_stage_model.encode_token_weights(tokens)
File "E:\ComfyUI_windows_portable\ComfyUI\comfy\sd1_clip.py", line 737, in encode_token_weights
out = getattr(self, self.clip).encode_token_weights(token_weight_pairs)
File "E:\ComfyUI_windows_portable\ComfyUI\comfy\sd1_clip.py", line 45, in encode_token_weights
o = self.encode(to_encode)
File "E:\ComfyUI_windows_portable\ComfyUI\comfy\sd1_clip.py", line 306, in encode
return self(tokens)
File "E:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
File "E:\ComfyUI_windows_portable\ComfyUI\comfy\sd1_clip.py", line 266, in forward
embeds, attention_mask, num_tokens, embeds_info = self.process_tokens(tokens, device)
~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\comfy\sd1_clip.py", line 213, in process_tokens
tokens_embed = self.transformer.get_input_embeddings()(tokens_embed, out_dtype=torch.float32)
File "E:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
File "E:\ComfyUI_windows_portable\ComfyUI\comfy\ops.py", line 633, in forward
return self.forward_comfy_cast_weights(*args, **kwargs)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\ComfyUI\comfy\ops.py", line 625, in forward_comfy_cast_weights
x = torch.nn.functional.embedding(input, weight, self.padding_idx, self.max_norm, self.norm_type, self.scale_grad_by_freq, self.sparse).to(dtype=output_dtype)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\functional.py", line 2567, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
🤖 AI解决方案
报错分析报告
1.错误翻译
原文：torch.AcceleratorError: CUDA error: no kernel image is available for execution on the device
译文：Torch加速器错误：CUDA错误：没有可用于在设备上执行的内核镜像
2. 原因分析
torch.nn.functional.embedding时触发CUDA内核调用，但设备无对应可执行镜像（堆栈中最后一步是torch.embedding）。3. 解决方案
#### 方案1：强制使用CPU运行（快速验证）
bash
ComfyUI启动命令添加--cpu参数（Windows便携版示例）
E:\ComfyUI_windows_portable\run_nvidia_gpu.bat --cpu
#### 方案2：代码中指定设备为CPU（若需修改源码）
python
在触发错误的代码前添加（如ComfyUI的nodes.py或启动脚本）
import torch
torch.device("cpu") # 强制使用CPU
或修改模型加载逻辑：model.to("cpu")
#### 方案3：安装匹配GPU的PyTorch版本（彻底解决）
nvidia-smi，看“CUDA Version”或查[NVIDIA显卡计算能力表](https://developer.nvidia.com/cuda-gpus)。 bash
pip install torch==2.0.1+cu113 torchvision==0.15.2+cu113 --extra-index-url https://download.pytorch.org/whl/cu113
4. 预防措施
torch.cuda.get_device_capability()查GPU计算能力，确保与CUDA版本匹配。 pip freeze > requirements.txt记录环境，避免自动升级导致不兼容。 -️ 推荐工具：
nvidia-smi（查GPU状态）、[PyTorch官网版本选择器](https://pytorch.org/get-started/locally/)（精准选版本）。---
注：若需进一步调试，可按报错提示设置CUDA_LAUNCH_BLOCKING=1（如export CUDA_LAUNCH_BLOCKING=1）获取准确堆栈。