mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-01 00:39:00 +01:00
parallel : minor
This commit is contained in:
parent
6028879f56
commit
7b7472ee26
@ -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());
|
||||
|
Loading…
Reference in New Issue
Block a user