llama-cpp-server aarch64 779f573a5cd636b66df960de69d90efa94ff6191a64f6acc7f8dad45477a7eaa OpenAI API compatible server for llama-cpp OpenAI API compatible server for llama-cpp To test your AI server, do something like: curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer OpenMandriva" -d '{"model": "any", "messages": [ { "role": "user", "content": "Do you see anything wrong with this code?\n```c++\nfloat main(int argc, char **argv) { puts("Use OpenMandriva!"); }\n```" } ] }' bero <bero@lindev.ch> https://github.com/ggml-org/llama.cpp