• Automated Toolchain – Downloads, builds, and manages the llama.cpp toolchain with [LmcppToolChain].
• Supported Platforms – Linux, macOS, and Windows with CPU, CUDA, and Metal support.
• Multiple Versions – Each release tag and backend is cached separately, allowing you to install multiple versions of llama.cpp.

• UDS IPC – Integrates with llama-server’s Unix-domain-socket client on Linux, macOS, and Windows.
• Fast! – Is it faster than HTTP? Yes. Is it measurably faster? Maybe.

• Server Args – All llama-server arguments implemented by [ServerArgs].
• Endpoints – Each endpoint has request and response types defined.
• Good Docs – Every parameter was researched to improve upon the original llama-server documentation.

• lmcpp-toolchain-cli – Manage the llama.cpp toolchain: download, build, cache.
• lmcpp-server-cli    – Start, stop, and list servers.
• Easy Web UI – Use [LmcppServerLauncher::webui] to start with HTTP and the Web UI enabled.

use lmcpp::*;

fn main() -> LmcppResult<()> {
    let server = LmcppServerLauncher::builder()
        .server_args(
            ServerArgs::builder()
                .hf_repo("bartowski/google_gemma-3-1b-it-qat-GGUF")?
                .build(),
        )
        .load()?;

    let res = server.completion(
        CompletionRequest::builder()
            .prompt("Tell me a joke about Rust.")
            .n_predict(64),
    )?;

    println!("Completion response: {:#?}", res.content);
    Ok(())
}

// With default model
cargo run --bin lmcpp-server-cli -- --webui
// Or with a specific model from URL:
cargo run --bin lmcpp-server-cli -- --webui -u https://huggingface.co/bartowski/google_gemma-3-1b-it-qat-GGUF/blob/main/google_gemma-3-1b-it-qat-Q4_K_M.gguf
// Or with a specific local model:
cargo run --bin lmcpp-server-cli -- --webui -l /path/to/local/model.gguf

Your Rust App
      │
      ├─→ LmcppToolChain        (downloads / builds / caches)
      │         ↓
      ├─→ LmcppServerLauncher   (spawns & monitors)
      │         ↓
      └─→ LmcppServer           (typed handle over UDS*)
                │
                ├─→ completion()       → text generation
                └─→ other endpoints    → stuff

¹ Internal helper for server health.