CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

examples : replace llama_kv_cache_seq_* with llama_past_seq_*

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-06-10 14:44:42 -04:00
parent 372482dffe
commit 43d8d4bf9e
23 changed files with 125 additions and 112 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/infill/infill.cpp
View File

@@ -380,8 +380,8 @@ int main(int argc, char ** argv) {
LOG("context full, swapping: n_past = %d, n_left = %d, n_ctx = %d, n_keep = %d, n_discard = %d\n",
n_past, n_left, n_ctx, params.n_keep, n_discard);
llama_kv_cache_seq_rm (ctx, 0, params.n_keep + 1 , params.n_keep + n_discard + 1);
llama_kv_cache_seq_add(ctx, 0, params.n_keep + 1 + n_discard, n_past, -n_discard);
llama_past_seq_rm (ctx, 0, params.n_keep + 1 , params.n_keep + n_discard + 1);
llama_past_seq_add(ctx, 0, params.n_keep + 1 + n_discard, n_past, -n_discard);
n_past -= n_discard;