CUDA: mul_mat_q=true llama_context_params default (#2912)

diff --git a/llama.cpp b/llama.cpp
index fcd6f276a065583abe9b98a2fa0653cc3ef7d305..95ee6ffe41c3a05d74d7e956649f1d2af13a822e 100644 (file)
--- a/llama.cpp
+++ b/llama.cpp
@@ -5287,7 +5287,7 @@ struct llama_context_params llama_context_default_params() {
         /*.progress_callback           =*/ nullptr,
         /*.progress_callback_user_data =*/ nullptr,
         /*.low_vram                    =*/ false,
-        /*.mul_mat_q                   =*/ false,
+        /*.mul_mat_q                   =*/ true,
         /*.f16_kv                      =*/ true,
         /*.logits_all                  =*/ false,
         /*.vocab_only                  =*/ false,