tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

parallel : increase the variability of the prompt lengths (#13927)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-05-30 19:38:07 +03:00
committed by GitHub
parent df0c0c7d02
commit dd665cc9d4
2 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/parallel/parallel.cpp
View File

@ -315,7 +315,10 @@ int main(int argc, char ** argv) {
} else {
client.prompt += k_system;
}
for (int i = 0; i < n_junk; ++i) {
const int n_junk_cur = rand() % n_junk;
for (int i = 0; i < n_junk_cur; ++i) {
const int r = rand() % k_questions.size();
client.prompt += "User:\n" + k_questions[r] + "\nAssistant:\n " + k_answers[r] + "\n";
}
@ -340,7 +343,7 @@ int main(int argc, char ** argv) {
client.n_decoded = 0;
client.i_batch = batch.n_tokens - 1;
LOG_INF("\033[31mClient %3d, seq %4d, started decoding ...\033[0m\n", client.id, client.seq_id);
LOG_INF("\033[31mClient %3d, seq %4d, junk = %4d, started decoding ...\033[0m\n", client.id, client.seq_id, n_junk_cur);
g_seq_id += 1;