When using the Qianwen model to generate a new image with a size of 2560*2560, an error occurred

### Custom Node Testing

- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

Sampe node has finished, but vae decode error

### Actual Behavior

When using the Qianwen model to generate a graph, if the size is 2560*2560, the vae node reports an error, causing comfyui to exit

### Steps to Reproduce

[qwen_demo.json](https://github.com/user-attachments/files/24702216/qwen_demo.json)

### Debug Logs

```powershell
terminate called after throwing an instance of 'c10::Error'
what(): CUDA error: an illegal memory access was encountered
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

Exception raised from c10_cuda_check_implementation at /pytorch/c10/cuda/CUDAException.cpp:43 (most recent call first):
frame #0: c10::Error::Error(c10::SourceLocation, std::string) + 0x96 (0x702d89d6c1b6 in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libc10.so)
frame #1: c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::string const&) + 0x64 (0x702d89d15a76 in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libc10.so)
frame #2: c10::cuda::c10_cuda_check_implementation(int, char const*, char const*, int, bool) + 0x118 (0x702d8a1a3918 in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libc10_cuda.so)
frame #3: + 0x60b30 (0x702d8a1a9b30 in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libc10_cuda.so)
frame #4: + 0x62024 (0x702d8a1ab024 in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libc10_cuda.so)
frame #5: + 0xe4042d (0x702d3806b42d in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so)
frame #6: + 0x108c153 (0x702d382b7153 in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so)
frame #7: + 0x108dd5f (0x702d382b8d5f in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so)
frame #8: + 0x108e6eb (0x702d382b96eb in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so)
frame #9: + 0x10710bd (0x702d3829c0bd in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so)
frame #10: at::native::cudnn_convolution(at::Tensor const&, at::Tensor const&, c10::ArrayRef, c10::ArrayRef, c10::ArrayRef, long, bool, bool, bool) + 0x53f (0x702d3829ca3f in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so)
frame #11: + 0x3674cee (0x702d3a89fcee in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so)
frame #12: + 0x368a791 (0x702d3a8b5791 in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so)
frame #13: at::_ops::cudnn_convolution::call(at::Tensor const&, at::Tensor const&, c10::ArrayRef, c10::ArrayRef, c10::ArrayRef, c10::SymInt, bool, bool, bool) + 0x31c (0x702d6ee7bd0c in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cpu.so)
frame #14: at::native::_convolution(at::Tensor const&, at::Tensor const&, std::optional const&, c10::ArrayRef, c10::ArrayRef, c10::ArrayRef, bool, c10::ArrayRef, long, bool, bool, bool, bool) + 0x1a73 (0x702d6e04f6f3 in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cpu.so)
frame #15: + 0x2e8a85f (0x702d6f25d85f in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cpu.so)
frame #16: + 0x2e9683c (0x702d6f26983c in /opt/environments/python/comfyui/lib/python3.10/site-packages/torch/lib/libtorch_cpu.so)
```

### Other

_No response_