# llama_cpp C+ bindings for [llama.cpp](https://github.com/ggml-org/llama.cpp)'s C API, in two layers: - **Raw FFI** generated straight from the upstream headers with [`cpc-bindgen`](/docs/tooling) (`build.sh`), so the binding tracks the C API rather than reimplementing it. - **A hand-written safe facade** — `Session`, with `load` / `generate` / `tokenize` / `decode` / `sample` — over that raw layer, so day-to-day use is ownership-safe C+ rather than raw pointers. It links `libllama` and `libmtmd`. Rather than baking an absolute path into the manifest, the `[link]` search-path reads an environment variable, so the same binding works on any machine that points `LLAMA_CPP_LIB` at its own build: ```toml [link] search-paths = ["${LLAMA_CPP_LIB}"] ``` See [Modules & packages](/docs/modules-and-packages) for the `[link]` table and `${VAR}` expansion. The `llama_cpp_smoke` recipe is **verified end to end**: it links against a current llama.cpp and runs real text generation on the Metal GPU (gemma-4-E2B). This is the runnable counterpart to the [field journal on porting ggml to C+](/blog/porting-llama-cpp-ggml-core-to-cplus).