diff options
| author | pudepiedj <pudepiedj@gmail.com> | 2024-01-11 16:14:52 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-11 18:14:52 +0200 |
| commit | 43f76bf1c362c067fce46bb8dcda0b64af8a9533 (patch) | |
| tree | c446cabb97601363b645f2fb661bc48d790478fa /llama.cpp | |
| parent | 2f043328e3116724d15b915b5c6078e2df860a69 (diff) | |
main : print total token count and tokens consumed so far (#4874)
* Token count changes
* Add show token count
* Updating before PR
* Two requested changes
* Move param def posn
Diffstat (limited to 'llama.cpp')
| -rw-r--r-- | llama.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -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) { |