diff --git a/examples/speculative/speculative.cpp b/examples/speculative/speculative.cpp index 64c960053..7b3af01f3 100644 --- a/examples/speculative/speculative.cpp +++ b/examples/speculative/speculative.cpp @@ -67,7 +67,7 @@ int main(int argc, char ** argv) { params.n_gpu_layers = params.n_gpu_layers_draft; if (params.n_threads_draft > 0) { params.n_threads = params.n_threads_draft; - } + } params.n_threads_batch = params.n_threads_batch_draft; std::tie(model_dft, ctx_dft) = llama_init_from_gpt_params(params);