Function load_model

subprojects/llama.cpp/tests/test-backend-sampler.cpp:30–69

};

static llama_model_ptr load_model(const test_args & args) {
    auto mparams = llama_model_default_params();

    ggml_backend_dev_t devs[2] = { nullptr, nullptr };

    if (args.device != "auto") {
        if (args.device == "gpu") {
            devs[0] = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_GPU);

            if (devs[0] == nullptr) {
                fprintf(stderr, "Error: GPU requested but not available\n");
                return nullptr;
            }

            mparams.n_gpu_layers = 999;
        } else if (args.device == "cpu") {
            devs[0] = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU);

            mparams.n_gpu_layers = 0;
        } else {
            fprintf(stderr, "Error: invalid device '%s'\n", args.device.c_str());
            return nullptr;
        }

        mparams.devices = devs;

        fprintf(stderr, "Using device: %s\n", ggml_backend_dev_name(devs[0]));
    }

    llama_model_ptr res;

    res.reset(llama_model_load_from_file(args.model.c_str(), mparams));

    if (!res) {
        fprintf(stderr, "Warning: failed to load model '%s', skipping test\n", args.model.c_str());
        return nullptr;
    }

    return res;
}

struct test_context {
    llama_context_ptr ctx;