root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-29 04:44:34 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

parallel : print misses on each request

Browse Source
This commit is contained in:
Georgi Gerganov 2023-09-19 23:50:05 +03:00
parent eed3fd4234
commit 6028879f56
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/parallel/parallel.cpp
View File

@ -326,12 +326,10 @@ int main(int argc, char ** argv) {
const auto t_main_end = ggml_time_us();
LOG_TEE("\033[1mClient %3d, seq %4d, prompt %4d t, response %4d t, time %5.2f s, speed: PP %5.2f t/s, TG %5.2f t/s, AVG %5.2f t/s \033[0m: \n\nInput: %s\nResponse: %s\n\n",
LOG_TEE("\033[1mClient %3d, seq %4d, prompt %4d t, response %4d t, time %5.2f s, cache miss %d \033[0m: \n\nInput: %s\nResponse: %s\n\n",
client.id, client.seq_id, client.n_prompt, client.n_decoded,
(t_main_end - client.t_start_prompt) / 1e6,
(double) (client.n_prompt ) / (client.t_start_gen - client.t_start_prompt) * 1e6,
(double) (client.n_decoded ) / (t_main_end - client.t_start_gen) * 1e6,
(double) (client.n_decoded + client.n_prompt) / (t_main_end - client.t_start_prompt) * 1e6,
n_cache_miss,
::trim(client.input).c_str(),
::trim(client.response).c_str());