tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 12:25:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into xsn/private_batch_api

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 15:55:18 +01:00
parent 46596caf6d be7c303410
commit 17f954c8e2
173 changed files with 26425 additions and 16117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/llama-bench/llama-bench.cpp
View File

@ -1580,7 +1580,7 @@ int main(int argc, char ** argv) {
test t(inst, lmodel, ctx);
llama_kv_cache_clear(ctx);
llama_kv_self_clear(ctx);
// cool off before the test
if (params.delay) {
@ -1620,7 +1620,7 @@ int main(int argc, char ** argv) {
}
for (int i = 0; i < params.reps; i++) {
llama_kv_cache_clear(ctx);
llama_kv_self_clear(ctx);
uint64_t t_start = get_time_ns();