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

main : print total token count and tokens consumed so far (#4874)

Browse source 
* Token count changes

* Add show token count

* Updating before PR

* Two requested changes

* Move param def posn
This commit is contained in:
pudepiedj 2024-01-11 16:14:52 +00:00 • committed by GitHub
parent 2f043328e3
commit 43f76bf1c3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 15 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -10921,7 +10921,7 @@ void llama_print_timings(struct llama_context * ctx) {
__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));
LLAMA_LOG_INFO("%s: total time = %10.2f ms / %5d tokens\n", __func__, (timings.t_end_ms - timings.t_start_ms), (timings.n_p_eval + timings.n_eval));
}
void llama_reset_timings(struct llama_context * ctx) {