tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : deprecate llama_kv_self_ API (#14030)

Browse Source 
* llama : deprecate llama_kv_self_ API

ggml-ci

* llama : allow llama_memory_(nullptr)

ggml-ci

* memory : add flag for optional data clear in llama_memory_clear

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-06 14:11:15 +03:00
committed by GitHub
parent 487a5e0401
commit 745aa5319b
34 changed files with 206 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@ -1900,7 +1900,7 @@ int main(int argc, char ** argv) {
test t(inst, lmodel, ctx);
llama_kv_self_clear(ctx);
llama_memory_clear(llama_get_memory(ctx), false);
// cool off before the test
if (params.delay) {
@ -1948,7 +1948,7 @@ int main(int argc, char ** argv) {
}
for (int i = 0; i < params.reps; i++) {
llama_kv_self_clear(ctx);
llama_memory_clear(llama_get_memory(ctx), false);
if (t.n_depth > 0) {
if (params.progress) {