[layers] fix assert bug when concat gate&up

Author: abenmao

CMakeLists.txt

@@ -183,6 +183,9 @@ add_definitions(-DAVX512_FP32_WEIGHT_ONLY_NF4=true)
 # add_definitions(-DSTEP_BY_STEP_ATTN=true)
 add_definitions(-DUSE_SHM=true)
 option(XFT_BUILD_TESTS "Build xfastertransformer unit tests" OFF)
+if(XFT_BUILD_TESTS)
+add_definitions(-DUNDEBUG=true)
+endif()
 
 # timeline event
 option(WITH_TIMELINE "Build with timeline event support" OFF)

src/layers/mlp_llama.h

@@ -13,6 +13,11 @@
 // limitations under the License.
 // ============================================================================
 #pragma once
+
+#ifdef UNDEBUG
+#undef NDEBUG
+#endif
+
 #include "bert_util.h"
 #include "copy_util.h"
 #include "debugger.h"
@@ -248,10 +253,7 @@ class LlamaMLP : public SingletonBase<LlamaMLP<WeiT>> {
         TimeLine t("DownProj");
 
         assert(input.Rows() == output.Rows());
-        if (!enableCATMLP())
-            assert(input.Cols() == downWeight.Rows());
-        else
-            assert(input.Cols() == 2 * downWeight.Rows());
+        assert(input.Cols() == downWeight.Rows());
         assert(downWeight.Cols() == output.Cols());
 
         int M = input.Rows(), N = output.Cols(), K = downWeight.Rows();