metal : enable mat-vec kernels for bs <= 4 (llama/10491)

diff --git a/ggml/src/ggml-metal/ggml-metal.m b/ggml/src/ggml-metal/ggml-metal.m
index ce7afc61c7c21b89a2bbd96f37651b757c63e75d..ae29b8b2e64a05a5527381b037241c965f89e233 100644 (file)
--- a/ggml/src/ggml-metal/ggml-metal.m
+++ b/ggml/src/ggml-metal/ggml-metal.m
@@ -1935,7 +1935,7 @@ static void ggml_metal_encode_node(
 
                 // find the break-even point where the matrix-matrix kernel becomes more efficient compared
                 // to the matrix-vector kernel
-                int ne11_mm_min = 1;
+                int ne11_mm_min = 4;
 
 #if 0
                 // the numbers below are measured on M2 Ultra for 7B and 13B models