Option to use MLA without a transposed cache (#235)

The `-mla` command line option turns into an int from a bool.
mla = 0: use standard attention
mla = 1: use MLA with transposed cache
mla > 1: use MLA without transposed cache

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

1 files changed, 1 insertions, 1 deletions

diff --git a/include/llama.h b/include/llama.h
index beb6ecba..2b33701c 100644
--- a/include/llama.h
+++ b/include/llama.h
@@ -383,7 +383,7 @@ extern "C" {
         bool embeddings;  // if true, extract embeddings (together with logits)
         bool offload_kqv; // whether to offload the KQV ops (including the KV cache) to GPU
         bool flash_attn;  // whether to use flash attention [EXPERIMENTAL]
-        bool mla_attn;    // whether to use MLA attention [EXPERIMENTAL]
+        int  mla_attn;    // whether to use MLA attention [EXPERIMENTAL]
         bool fused_moe_up_gate; // whether to use fused MoE up/down op [EXPERIMENTAL]
 
         // Abort callback