Function main

tools/server/server.cpp:74–353

}

int main(int argc, char ** argv) {
    std::setlocale(LC_NUMERIC, "C");

    // own arguments required by this example
    common_params params;

    common_init();

    if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_SERVER)) {
        return 1;
    }

    // validate batch size for embeddings
    // embeddings require all tokens to be processed in a single ubatch
    // see https://github.com/ggml-org/llama.cpp/issues/12836
    if (params.embedding && params.n_batch > params.n_ubatch) {
        LOG_WRN("%s: embeddings enabled with n_batch (%d) > n_ubatch (%d)\n", __func__, params.n_batch, params.n_ubatch);
        LOG_WRN("%s: setting n_batch = n_ubatch = %d to avoid assertion failure\n", __func__, params.n_ubatch);
        params.n_batch = params.n_ubatch;
    }

    if (params.n_parallel < 0) {
        LOG_INF("%s: n_parallel is set to auto, using n_parallel = 4 and kv_unified = true\n", __func__);

        params.n_parallel = 4;
        params.kv_unified = true;
    }

    // for consistency between server router mode and single-model mode, we set the same model name as alias
    if (params.model_alias.empty() && !params.model.name.empty()) {
        params.model_alias.insert(params.model.name);
    }

    // struct that contains llama context and inference
    server_context ctx_server;

    llama_backend_init();
    llama_numa_init(params.numa);

    LOG_INF("build_info: %s\n", llama_build_info());
    LOG_INF("%s\n", common_params_get_system_info(params).c_str());

    server_http_context ctx_http;
    if (!ctx_http.init(params)) {
        LOG_ERR("%s: failed to initialize HTTP server\n", __func__);
        return 1;
    }

    //
    // Router
    //

    // register API routes
    server_routes routes(params, ctx_server);
    server_tools tools;

    bool is_router_server = params.model.path.empty();
    std::optional<server_models_routes> models_routes{};