diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 47bea15913600..8feff67029da1 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -884,7 +884,8 @@ struct server_context { bool launch_slot_with_task(server_slot & slot, const server_task & task) { slot_params default_params; - llama_sampling_params default_sparams; + // Sampling parameter defaults are loaded from the global server context (but individual requests can still override them) + llama_sampling_params default_sparams = params.sparams; auto & data = task.data; if (data.count("__oaicompat") != 0) {