upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-07 02:20:48 -05:00
Code Issues Packages Projects Releases Wiki Activity

Generate full token count during warm up

Browse Source 
Signed-off-by: Joe Todd <joe.todd@codeplay.com>
This commit is contained in:
Joe Todd
2024-06-28 13:29:00 +01:00
parent 38373cfbab
commit 712e4d9450
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/llama-bench/llama-bench.cpp
View File

@@ -1390,7 +1390,7 @@ int main(int argc, char ** argv) {
test_prompt(ctx, t.n_prompt, 0, t.n_batch, t.n_threads);
}
if (t.n_gen > 0) {
test_gen(ctx, 1, 0, t.n_threads);
test_gen(ctx, t.n_gen, 0, t.n_threads);
}
for (int i = 0; i < params.reps; i++) {