mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-05-14 04:54:06 +00:00
cont : handle non-ckpt models
This commit is contained in:
@@ -2101,7 +2101,7 @@ bool server_prompt_cache::load(server_prompt & prompt, const server_tokens & tok
|
||||
data.clear();
|
||||
data.shrink_to_fit();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
prompt = std::move(*it_best);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user