fix: use pre-compiled llama-cpp-python wheel + model in image

fix: bake GGUF model into Docker image during build

fix: use pre-compiled llama-server binary (zero compilation)

fix: use ninja-build + CMAKE_ARGS for llama-cpp-python build

fix: add cmake+build-essential for llama-cpp

fix: add libgomp1 for llama-cpp runtime

opt: use pre-built wheel for faster build

init