Function main

tests/export-graph-ops.cpp:128–226

}

int main(int argc, char ** argv) {
    common_params params;
    params.out_file = "tests.txt";

    common_init();

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

    // Load CPU-only
    ggml_backend_dev_t cpu_device = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU);
    params.devices = { cpu_device, nullptr };
    params.fit_params = false;
    params.n_gpu_layers = 0;

    params.warmup = false;

    llama_context * ctx;
    common_init_result_ptr init_result;
    llama_context_ptr ctx2;
    llama_model_ptr model;

    if (params.model.hf_repo.empty()) {
        init_result = common_init_from_params(params);

        ctx = init_result->context();
    } else {
#ifdef LLAMA_HF_FETCH
        auto [hf_repo, hf_quant] = common_download_split_repo_tag(params.model.hf_repo);
        if (hf_quant.empty() || hf_quant == "latest") {
            hf_quant = "Q4_K_M";
        }

        gguf_context_ptr gguf_ctx = gguf_fetch_gguf_ctx(hf_repo, hf_quant);
        if (!gguf_ctx) {
            LOG_ERR("failed to fetch GGUF metadata from %s\n", hf_repo.c_str());
            return 1;
        }

        llama_model_params model_params = llama_model_default_params();
        model_params.devices = params.devices.data();
        model_params.no_alloc = true;

        model.reset(llama_model_init_from_user(gguf_ctx.get(), set_tensor_data, nullptr, model_params));

        if (!model) {
            LOG_ERR("failed to create llama_model from %s\n", hf_repo.c_str());
            return 1;
        }

        llama_context_params ctx_params = llama_context_default_params();
        ctx2.reset(llama_init_from_model(model.get(), ctx_params));
        ctx = ctx2.get();

        if (!ctx) {
            LOG_ERR("failed to create llama_context\n");
            return 1;