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

Two requested changes

Browse source
This commit is contained in:
pudepiedj 2024-01-11 15:55:06 +00:00
parent 74c469dbdb
commit 81be5d2c51
2 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/main/main.cpp
View file

@ -659,7 +659,7 @@ int main(int argc, char ** argv) {
if (!embd.empty() && !path_session.empty()) { if (!embd.empty() && !path_session.empty()) {
session_tokens.insert(session_tokens.end(), embd.begin(), embd.end()); session_tokens.insert(session_tokens.end(), embd.begin(), embd.end());
n_session_consumed = session_tokens.size(); n_session_consumed = session_tokens.size();
} }
} }
embd.clear(); embd.clear();

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); __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", 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); __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 / %5d tokens\n", __func__, (timings.t_end_ms - timings.t_start_ms), (timings.n_sample + timings.n_p_eval + timings.n_eval)); 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) { void llama_reset_timings(struct llama_context * ctx) {