CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

parallel : process system prompt once + configurable paramters + llama API

Browse Source
This commit is contained in:
Georgi Gerganov
2023-09-19 17:00:42 +03:00
parent 82e20e9ba0
commit 4b5f3cd6bf
9 changed files with 187 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -977,7 +977,7 @@ int main(int argc, char ** argv) {
test t(inst, lmodel, ctx);
llama_kv_cache_rm_tokens(ctx, -1, -1);
llama_kv_cache_tokens_rm(ctx, -1, -1);
// warmup run
if (t.n_prompt > 0) {
@@ -988,7 +988,7 @@ int main(int argc, char ** argv) {
}
for (int i = 0; i < params.reps; i++) {
llama_kv_cache_rm_tokens(ctx, -1, -1);
llama_kv_cache_tokens_rm(ctx, -1, -1);
uint64_t t_start = get_time_ns();
if (t.n_prompt > 0) {