CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

parallel : minor

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-20 00:35:10 +03:00
parent 6028879f56
commit 7b7472ee26
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/parallel/parallel.cpp
View File

@@ -326,9 +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, cache miss %d \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, speed %5.2f t/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.n_decoded) / (t_main_end - client.t_start_prompt) * 1e6,
n_cache_miss,
::trim(client.input).c_str(),
::trim(client.response).c_str());