Function test_backends

tests/test-llama-archs.cpp:470–605

}

static int test_backends(const llm_arch target_arch, const size_t seed, const ggml_log_level log_level) {
    struct user_data_t {
        struct {
            ggml_log_callback callback;
            void * user_data;
        } original_logger;
        ggml_log_level min_level; // prints below this log level go to debug log
    };
    user_data_t ud;
    llama_log_get(&ud.original_logger.callback, &ud.original_logger.user_data);
    ud.min_level = log_level;

    llama_log_set([](ggml_log_level level, const char * text, void * user_data) {
        const user_data_t * ud = (const user_data_t *) user_data;
        const ggml_log_level level_eff = level >= ud->min_level ? level : GGML_LOG_LEVEL_DEBUG;
        ud->original_logger.callback(level_eff, text, ud->original_logger.user_data);
    }, &ud);

    const std::vector<llama_token> tokens = get_tokens(128, 128, seed);

    struct device_config {
        std::vector<ggml_backend_dev_t> devs;
        std::string                     label;
        llama_split_mode                split_mode;

        device_config(std::vector<ggml_backend_dev_t> devs, std::string name, llama_split_mode split_mode)
            : devs(std::move(devs)), label(std::move(name)), split_mode(split_mode) {}
    };

    std::vector<device_config> dev_configs;
    {
        std::vector<ggml_backend_dev_t> devices_meta;
        {
            const size_t device_count = ggml_backend_dev_count();
            for (size_t i = 0; i < device_count; i++) {
                ggml_backend_dev_t dev = ggml_backend_dev_get(i);
                dev_configs.emplace_back(std::vector<ggml_backend_dev_t>{dev}, ggml_backend_dev_description(dev), LLAMA_SPLIT_MODE_LAYER);

                // cpu-based devices cannot be used in tensor split mode
                if (ggml_backend_dev_buffer_type(dev) != ggml_backend_cpu_buffer_type()) {
                    devices_meta.push_back(dev);
                }
            }
        }

        dev_configs.emplace_back(devices_meta, "Meta", LLAMA_SPLIT_MODE_TENSOR);
    }

    bool all_ok = true;
    common_log_flush(common_log_main());
    printf("|%16s|%30s|%6s|%15s|%9s|\n", "Model arch.", "Device", "Config", "NMSE vs. CPU", "Roundtrip");
    printf("|----------------|------------------------------|------|---------------|---------|\n");
    for (const llm_arch & arch : llm_arch_all()) {
        if (arch == LLM_ARCH_UNKNOWN) {
            continue;
        }
        if (target_arch != LLM_ARCH_UNKNOWN && arch != target_arch) {
            continue;