Function llama_print_timings

llama.cpp:10843–10855

}

void llama_print_timings(struct llama_context * ctx) {
    const llama_timings timings = llama_get_timings(ctx);

    LLAMA_LOG_INFO("\n");
    LLAMA_LOG_INFO("%s:        load time = %10.2f ms\n", __func__, timings.t_load_ms);
    LLAMA_LOG_INFO("%s:      sample time = %10.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
            __func__, timings.t_sample_ms, timings.n_sample, timings.t_sample_ms / timings.n_sample, 1e3 / timings.t_sample_ms * timings.n_sample);
    LLAMA_LOG_INFO("%s: prompt eval time = %10.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n",
            __func__, timings.t_p_eval_ms, timings.n_p_eval, timings.t_p_eval_ms / timings.n_p_eval, 1e3 / timings.t_p_eval_ms * timings.n_p_eval);
    LLAMA_LOG_INFO("%s:        eval time = %10.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
            __func__, timings.t_eval_ms, timings.n_eval, timings.t_eval_ms / timings.n_eval, 1e3 / timings.t_eval_ms * timings.n_eval);
    LLAMA_LOG_INFO("%s:       total time = %10.2f ms\n", __func__, (timings.t_end_ms - timings.t_start_ms));
}

void llama_reset_timings(struct llama_context * ctx) {
    ctx->t_start_us = ggml_time_us();