speculative : threading options (#4959)

* speculative: expose draft threading

* fix usage format

* accept -td and -tbd args

* speculative: revert default behavior when -td is unspecified

* fix trailing whitespace

1 files changed, 4 insertions, 0 deletions

diff --git a/examples/speculative/speculative.cpp b/examples/speculative/speculative.cpp
index 20f1fb5b..7b3af01f 100644
--- a/examples/speculative/speculative.cpp
+++ b/examples/speculative/speculative.cpp
@@ -65,6 +65,10 @@ int main(int argc, char ** argv) {
     // load the draft model
     params.model = params.model_draft;
     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);
 
     {