mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-24 13:28:50 +01:00
Added tokens per second to info prints (#1928)
This commit is contained in:
parent
0ede372a51
commit
b24c3049d9
@ -3467,9 +3467,12 @@ void llama_print_timings(struct llama_context * ctx) {
|
||||
|
||||
fprintf(stderr, "\n");
|
||||
fprintf(stderr, "%s: load time = %8.2f ms\n", __func__, ctx->t_load_us / 1000.0);
|
||||
fprintf(stderr, "%s: sample time = %8.2f ms / %5d runs (%8.2f ms per token)\n", __func__, 1e-3 * ctx->t_sample_us, n_sample, 1e-3 * ctx->t_sample_us / n_sample);
|
||||
fprintf(stderr, "%s: prompt eval time = %8.2f ms / %5d tokens (%8.2f ms per token)\n", __func__, 1e-3 * ctx->t_p_eval_us, n_p_eval, 1e-3 * ctx->t_p_eval_us / n_p_eval);
|
||||
fprintf(stderr, "%s: eval time = %8.2f ms / %5d runs (%8.2f ms per token)\n", __func__, 1e-3 * ctx->t_eval_us, n_eval, 1e-3 * ctx->t_eval_us / n_eval);
|
||||
fprintf(stderr, "%s: sample time = %8.2f ms / %5d runs (%8.2f ms per token, %8.2f tokens per second)\n",
|
||||
__func__, 1e-3 * ctx->t_sample_us, n_sample, 1e-3 * ctx->t_sample_us / n_sample, 1e6 / ctx->t_sample_us * n_sample);
|
||||
fprintf(stderr, "%s: prompt eval time = %8.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n",
|
||||
__func__, 1e-3 * ctx->t_p_eval_us, n_p_eval, 1e-3 * ctx->t_p_eval_us / n_p_eval, 1e6 / ctx->t_p_eval_us * n_p_eval);
|
||||
fprintf(stderr, "%s: eval time = %8.2f ms / %5d runs (%8.2f ms per token, %8.2f tokens per second)\n",
|
||||
__func__, 1e-3 * ctx->t_eval_us, n_eval, 1e-3 * ctx->t_eval_us / n_eval, 1e6 / ctx->t_eval_us * n_eval);
|
||||
fprintf(stderr, "%s: total time = %8.2f ms\n", __func__, (t_end_us - ctx->t_start_us)/1000.0);
|
||||
}
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user