tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 20:45:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix defrag bugs + add parameter (#5735)

Browse Source 
* llama : fix defrag bugs + enable by default

ggml-ci

* llama : add defrag_thold parameter

ggml-ci

* llama : cont

* llama : disable log message

ggml-ci

* llama : fix graph size check during defrag
This commit is contained in:
Georgi Gerganov
2024-02-27 14:35:51 +02:00
committed by GitHub
parent cbbd1efa06
commit 9d533a77d0
5 changed files with 82 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/passkey/passkey.cpp
View File

@ -182,7 +182,7 @@ int main(int argc, char ** argv) {
llama_kv_cache_seq_rm (ctx, 0, n_keep , n_keep + n_discard);
llama_kv_cache_seq_add(ctx, 0, n_keep + n_discard, n_ctx, -n_discard);
llama_kv_cache_defrag (ctx);
//llama_kv_cache_defrag (ctx);
llama_kv_cache_update (ctx);
n_past = llama_kv_cache_seq_pos_max(ctx, 0) + 1;
@ -213,7 +213,7 @@ int main(int argc, char ** argv) {
llama_kv_cache_seq_rm (ctx, 0, n_keep , n_keep + n_discard);
llama_kv_cache_seq_add(ctx, 0, n_keep + n_discard, n_ctx, -n_discard);
llama_kv_cache_defrag (ctx);
//llama_kv_cache_defrag (ctx);
llama_kv_cache_update (ctx);
n_past = llama_kv_cache_seq_pos_max(ctx, 0) + 1;