haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

Added tokens per second to info prints (#1928)

Browse source
This commit is contained in:
Johannes Gäßler 2023-06-18 17:41:26 +02:00 committed by GitHub
parent 0ede372a51
commit b24c3049d9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
llama.cpp
View file

@ -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);
}