diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 8d072878c..e181e2e9f 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -841,12 +841,12 @@ struct server_context { } if (slot.n_predict > 0 && slot.params.n_predict > slot.n_predict) { + // Might be better to reject the request with a 400 ? LOG_WARNING("Max tokens to predict exceeds server configuration", { {"params.n_predict", slot.params.n_predict}, {"slot.n_predict", slot.n_predict}, }); - error_message = "Max tokens to predict exceeds server configuration"; - return false; + slot.params.n_predict = slot.n_predict; } // infill