mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-29 08:41:22 +00:00
server : purge slots one by one
This commit is contained in:
@@ -2731,6 +2731,9 @@ struct server_context {
|
|||||||
slot.prompt.tokens.clear();
|
slot.prompt.tokens.clear();
|
||||||
|
|
||||||
res = true;
|
res = true;
|
||||||
|
|
||||||
|
// purge slots one by one
|
||||||
|
break;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user