diff options
| author | pudepiedj <pudepiedj@gmail.com> | 2023-10-06 14:16:38 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-10-06 16:16:38 +0300 |
| commit | a8777ad84e00cda0399e827cdf971e2c3fab1da2 (patch) | |
| tree | 03be5a38a4db7507579cb7d13ed9428834c12f87 /llama.cpp | |
| parent | 97af49fa395df77e4c18af0e1655b2fee67c9686 (diff) | |
parallel : add option to load external prompt file (#3416)
* Enable external file and add datestamp
* Add name of external file at end
* Upload ToK2024
* Delete ToK2024.txt
* Experiments with jeopardy
* Move ParallelQuestions to /proimpts and rename
* Interim commit
* Interim commit
* Final revision
* Remove trailing whitespace
* remove cmake_all.sh
* Remove cmake_all.sh
* Changed .gitignore
* Improved reporting and new question files.
* Corrected typo
* More LLM questions
* Update LLM-questions.txt
* Yet more LLM-questions
* Remove jeopardy results file
* Reinstate original jeopardy.sh
* Update examples/parallel/parallel.cpp
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'llama.cpp')
| -rw-r--r-- | llama.cpp | 10 |
1 files changed, 5 insertions, 5 deletions
@@ -8219,14 +8219,14 @@ void llama_print_timings(struct llama_context * ctx) { const llama_timings timings = llama_get_timings(ctx); LLAMA_LOG_INFO("\n"); - LLAMA_LOG_INFO("%s: load time = %8.2f ms\n", __func__, timings.t_load_ms); - LLAMA_LOG_INFO("%s: sample time = %8.2f ms / %5d runs (%8.2f ms per token, %8.2f tokens per second)\n", + LLAMA_LOG_INFO("%s: load time = %10.2f ms\n", __func__, timings.t_load_ms); + LLAMA_LOG_INFO("%s: sample time = %10.2f ms / %5d runs (%8.2f ms per token, %8.2f tokens per second)\n", __func__, timings.t_sample_ms, timings.n_sample, timings.t_sample_ms / timings.n_sample, 1e3 / timings.t_sample_ms * timings.n_sample); - LLAMA_LOG_INFO("%s: prompt eval time = %8.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n", + LLAMA_LOG_INFO("%s: prompt eval time = %10.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n", __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 = %8.2f 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); - LLAMA_LOG_INFO("%s: total time = %8.2f ms\n", __func__, (timings.t_end_ms - timings.t_start_ms)); + LLAMA_LOG_INFO("%s: total time = %10.2f ms\n", __func__, (timings.t_end_ms - timings.t_start_ms)); } void llama_reset_timings(struct llama_context * ctx) { |