Function main

tools/mtmd/debug/mtmd-debug.cpp:50–229

}

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

    ggml_time_init();

    common_params params;

    common_init();

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

    mtmd_helper_log_set(common_log_default_callback, nullptr);

    if (params.mmproj.path.empty()) {
        show_additional_info(argc, argv);
        LOG_ERR("ERR: Missing --mmproj argument\n");
        return 1;
    }

    LOG_INF("%s: loading model: %s\n", __func__, params.model.path.c_str());

    mtmd::context_ptr ctx_mtmd;
    common_init_result_ptr llama_init;
    base_callback_data cb_data;

    llama_init = common_init_from_params(params);
    {
        auto * model = llama_init->model();
        const char * clip_path = params.mmproj.path.c_str();
        mtmd_context_params mparams = mtmd_context_params_default();
        mparams.use_gpu          = params.mmproj_use_gpu;
        mparams.print_timings    = true;
        mparams.n_threads        = params.cpuparams.n_threads;
        mparams.flash_attn_type  = params.flash_attn_type;
        mparams.warmup           = params.warmup;
        mparams.image_min_tokens = params.image_min_tokens;
        mparams.image_max_tokens = params.image_max_tokens;
        {
            // always enable debug callback
            mparams.cb_eval_user_data = &cb_data;
            mparams.cb_eval = common_debug_cb_eval<false>;
        }
        ctx_mtmd.reset(mtmd_init_from_file(clip_path, model, mparams));
        if (!ctx_mtmd.get()) {
            LOG_ERR("Failed to load vision model from %s\n", clip_path);
            exit(1);
        }
    }

    std::string input;
    int32_t inp_size = params.n_predict;
    if (params.image.empty()) {
        LOG_ERR("ERR: At least one of --image or --audio must be specified\n");
        return 1;
    }
    if (inp_size <= 0) {