hobpond

I had the same error. What resolved it for me was updating my environment to use pytorch-cuda=11.8 and downloaded https://developer.nvidia.com/cuda-11-8-0-download-archive. Seems like my pytorch-cuda for my environment was not compatible....

Have you tried Continue.dev, an extension for VSCode? You can load the model with llama.cpp and add Deepseek as the model to use. Here's my config (in the continue.dev text...