mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-18 05:56:00 -04:00
server : test alternative LRU logic
This commit is contained in:
@@ -2188,6 +2188,7 @@ struct server_context {
|
|||||||
if (!ret || slot.t_last_used <= t_last) {
|
if (!ret || slot.t_last_used <= t_last) {
|
||||||
t_last = slot.t_last_used;
|
t_last = slot.t_last_used;
|
||||||
ret = &slot;
|
ret = &slot;
|
||||||
|
break; // TMP: always pick the first non-processing slot
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
Reference in New Issue
Block a user