1 files changed, 1 insertions, 1 deletions
diff --git a/src/llama.cpp b/src/llama.cpp
index 395b2879..24737265 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -13896,7 +13896,7 @@ struct llm_build_context {
 
         // whether to use n_tokens as the matrix dimension during multiplication or n_head
         // n_tokens is higher during prompt processing, this allows to optimize for this case
-        bool pp_opt = n_tokens > n_head;
+        bool pp_opt = n_tokens >= 128; // Is it a fixed constant or is it somehow relared to n_head? original: n_tokens > n_head;
 
         for (int il = 0; il < n_layer; ++il) {
             struct ggml_tensor * inpSA = inpL;