tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-12 19:37:53 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : minor sampling refactor (2) (#9386)

Browse Source
This commit is contained in:
slaren
2024-09-09 17:10:46 +02:00
committed by GitHub
parent 38ca6f644b
commit 5fb5e24811
12 changed files with 115 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@@ -613,7 +613,7 @@ struct server_context {
gpt_params params;
llama_batch batch;
llama_batch batch = {};
bool clean_kv_cache = true;
bool add_bos_token = true;