CUDA error: no kernel image is available for execution on the device
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.1050显卡跑ComfyUI 出现上面的错误
原因：Torch 2.7.1 不再支持 Maxwell 和 Pascal 显卡，因此该版本及更高版本对 CUDA 功能的最低支持要求为 7.0。您必须将 Torch 降级至 2.7.0
重新安装依赖
pip install typing_extensions==4.15.0 torch==2.7.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
