vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add llama_kv_cache_compress (EXPERIMENTAL)

Browse source
This commit is contained in:
Georgi Gerganov 2024-02-25 22:16:13 +02:00
parent c24a2a6e60
commit 14d757066b
No known key found for this signature in database
GPG key ID: BF970631944C16B7
3 changed files with 262 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/passkey/passkey.cpp
View file

@ -148,6 +148,7 @@ int main(int argc, char ** argv) {
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_compress(ctx, 0);
llama_kv_cache_update (ctx);
n_past = llama_kv_cache_seq_pos_max(ctx, 0) + 1;