Not 100% sure what you've tried, but perhaps your docker image only has CUDA runtime installed and not CUDA development files? You could try adding a build step using one of Nvidia's "devel" docker ...
为 Windows 平台预编译的 llama-cpp-python 安装包，支持 Intel Arc GPU (SYCL) 加速。 基于 JamePeng 的分支 编译，为 Intel Arc GPU 提供 SYCL 加速支持。 0.3.38 llama_cpp_python-0.3.38+sycl-cp313-cp313-win_amd64.whl ~22 MB 0.3.36 ...
GGUF parser vulnerabilities disclosed May 15, 2026 include a critical integer overflow that lets any malicious model file ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results