CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : use 4 slots + unified KV by default

Browse Source
This commit is contained in:
Georgi Gerganov
2025-10-30 20:15:34 +02:00
parent a5d27aafe3
commit 2d69109dc1
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
tools/server/server.cpp
View File

@@ -4432,6 +4432,13 @@ int main(int argc, char ** argv) {
return 1; return 1;
} }
if (params.n_parallel == 1 && params.kv_unified == false) {
LOG_WRN("%s: setting n_parallel = 4 and kv_unified = true\n", __func__);
params.n_parallel = 4;
params.kv_unified = true;
}
common_init(); common_init();
// struct that contains llama context and inference // struct that contains llama context and inference