ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 02:41:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Revert kv cache name changes

Browse Source
This commit is contained in:
firecoperana
2026-01-17 08:42:43 -06:00
parent 79185862e5
commit 93abfb66ab
15 changed files with 62 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/passkey/passkey.cpp
View File

@@ -126,8 +126,8 @@ int main(int argc, char ** argv) {
const int ib = i/n_batch - 1;
const int bd = n_batch_grp*(n_grp - 1);
llama_memory_seq_add (ctx, 0, n_past - n_batch, n_past, ib*bd);
llama_memory_seq_div (ctx, 0, n_past - n_batch + ib*bd, n_past + ib*bd, n_grp);
llama_kv_cache_seq_add (ctx, 0, n_past - n_batch, n_past, ib*bd);
llama_kv_cache_seq_div (ctx, 0, n_past - n_batch + ib*bd, n_past + ib*bd, n_grp);
llama_kv_cache_update (ctx);
n_past = llama_kv_cache_seq_pos_max(ctx, 0) + 1;
@@ -160,8 +160,8 @@ int main(int argc, char ** argv) {
LOG_TEE("%s: shifting KV cache with %d\n", __func__, n_discard);
llama_memory_seq_rm (ctx, 0, n_keep , n_keep + n_discard);
llama_memory_seq_add(ctx, 0, n_keep + n_discard, n_ctx, -n_discard);
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_update (ctx);
@@ -191,8 +191,8 @@ int main(int argc, char ** argv) {
if (n_discard > 0) {
LOG_TEE("%s: shifting KV cache with %d to free space for the answer\n", __func__, n_discard);
llama_memory_seq_rm (ctx, 0, n_keep , n_keep + n_discard);
llama_memory_seq_add(ctx, 0, n_keep + n_discard, n_ctx, -n_discard);
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_update (ctx);