sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-01 22:54:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix model count exceeded check

Browse Source
This commit is contained in:
Ruben Ortlam
2026-04-02 11:39:36 +02:00
parent f750bae2d3
commit f4a384b46c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/server-models.cpp
View File

@@ -579,7 +579,7 @@ void server_models::unload_lru(const model_memory_map& new_model_memory_per_devi
memory_exceeded = get_memory_exceeded(new_model_memory_per_device);
}
bool count_exceeded = base_params.models_max > 0 &&
(count_active + 1) >= (size_t)base_params.models_max;
(count_active + 1) > (size_t)base_params.models_max;
if (!lru_model_name.empty() && (count_exceeded || memory_exceeded > 0)) {
SRV_INF("limits reached (count=%zu, memory margin exceeded on %zu device(s)), removing LRU name=%s\n",