Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-03 17:51:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama : zero KV cache used upon clear

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2023-11-22 19:30:48 +02:00
parent 79cb8f0040
commit 671f639c59
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llama.cpp
View File

@ -1629,6 +1629,7 @@ static void llama_kv_cache_clear(struct llama_kv_cache & cache) {
cache.cells[i].seq_id.clear(); cache.cells[i].seq_id.clear();
} }
cache.head = 0; cache.head = 0;
cache.used = 0;
} }
static void llama_kv_cache_seq_rm( static void llama_kv_cache_seq_rm(