diff --git a/.gitmodules b/.gitmodules
index 2b36e4928..697f3ef47 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -1,4 +1,4 @@
 [submodule "3rdparty/llama.cpp"]
 	path = 3rdparty/llama.cpp
-	url = https://github.com/Eddie-Wang1120/llama.cpp.git
-	branch = merge-dev
+	url = https://github.com/EthanPeng-2048/bitllama.cpp.git
+	branch = main
diff --git a/3rdparty/llama.cpp b/3rdparty/llama.cpp
index 1f86f058d..972fbfc73 160000
--- a/3rdparty/llama.cpp
+++ b/3rdparty/llama.cpp
@@ -1 +1 @@
-Subproject commit 1f86f058de0c3f4098dedae2ae8653c335c868a1
+Subproject commit 972fbfc7383dc5cfe976680fb51114a3f631cdda
diff --git a/src/ggml-bitnet-mad.cpp b/src/ggml-bitnet-mad.cpp
index 4ba9d6509..019e25c7c 100644
--- a/src/ggml-bitnet-mad.cpp
+++ b/src/ggml-bitnet-mad.cpp
@@ -808,7 +808,7 @@ void ggml_vec_dot_i2_i8_s_Nx1(int n, float * s, size_t bs, const void * vx, size
             accu[iy] = _mm256_setzero_si256();
         }
 
-        int8_t * y_col = y + col * by;
+        const int8_t * y_col = y + col * by;
         
         for (int i = 0; i < group32_num; i++) {
             const uint8_t *px = x + i * 1024;
@@ -1053,4 +1053,4 @@ void ggml_vec_dot_i2_i8_s(int n, float * s, size_t bs, const void * vx, size_t b
     {
         ggml_vec_dot_i2_i8_s_1x1(n, s, bs, vx, bx, vy, by, nrc);
     }
-}
\ No newline at end of file
+}