diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
index cca1303ab9..cd5d613e1f 100644
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
@@ -160,7 +160,7 @@ struct DeviceOperationInstanceFactory<
             }
         }
 #endif
-#if(defined(CK_ENABLE_BF16) && defined(CK_ENABLE_FP8))
+#if(defined(CK_ENABLE_BF16) && defined(CK_ENABLE_FP8) && defined(CK_USE_WMMA_FP8))
         if constexpr(is_same_v<ADataType, f8_t> && is_same_v<BDataType, f8_t> &&
                      is_same_v<CDataType, bhalf_t>)
         {
@@ -185,8 +185,7 @@ struct DeviceOperationInstanceFactory<
                     op_ptrs);
             }
         }
-#endif
-#if(defined(CK_ENABLE_BF16) && defined(CK_ENABLE_FP8))
+
         if constexpr(is_same_v<ADataType, bhalf_t> && is_same_v<BDataType, pk_i4_t> &&
                      is_same_v<CDataType, bhalf_t>)
         {
@@ -204,7 +203,7 @@ struct DeviceOperationInstanceFactory<
             }
         }
 #endif
-#if(defined(CK_ENABLE_FP16) && defined(CK_ENABLE_FP8))
+#if(defined(CK_ENABLE_FP16) && defined(CK_ENABLE_FP8) && defined(CK_USE_WMMA_FP8))
         if constexpr(is_same_v<ADataType, f8_t> && is_same_v<BDataType, half_t> &&
                      is_same_v<CDataType, half_t>)
         {
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc
index 99c06e7604..80414898ca 100644
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal_wmma.inc
@@ -155,7 +155,7 @@ void add_device_gemm_wmma_universal_bf16_bf16_bf16_km_nk_mn_comp_mnkpadding_inst
         DeviceGemmV2<Col, Col, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 #endif
-#if(defined(CK_ENABLE_BF16) && defined(CK_ENABLE_FP8))
+#if(defined(CK_ENABLE_BF16) && defined(CK_ENABLE_FP8) && defined(CK_USE_WMMA_FP8))
 void add_device_gemm_wmma_universal_f8_f8_bf16_mk_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, F8, F8, BF16, PassThrough, PassThrough, PassThrough>>>&
@@ -215,7 +215,7 @@ void add_device_gemm_wmma_universal_bf16_i4_bf16_km_nk_mn_comp_default_instances
         DeviceGemmV2<Col, Col, Row, BF16, I4, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances);
 #endif
-#if(defined(CK_ENABLE_FP16) && defined(CK_ENABLE_FP8))
+#if(defined(CK_ENABLE_FP16) && defined(CK_ENABLE_FP8) && defined(CK_USE_WMMA_FP8))
 void add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
diff --git a/test/gemm_universal/test_gemm_universal_wmma_bf16.cpp b/test/gemm_universal/test_gemm_universal_wmma_bf16.cpp
index f8c8d6efb1..311c4de32d 100644
--- a/test/gemm_universal/test_gemm_universal_wmma_bf16.cpp
+++ b/test/gemm_universal/test_gemm_universal_wmma_bf16.cpp
@@ -59,7 +59,7 @@ using KernelTypes_MK_KN = ::testing::Types<
 
 using KernelTypes_MK_NK = ::testing::Types<
     //         ADataType, BDataType, ComputeDataType, CDataType
-#if defined(CK_ENABLE_FP8) 
+#if defined(CK_ENABLE_FP8)
     std::tuple<     BF16,        I4,            BF16,      BF16>,
 #endif
     std::tuple<     BF16,      BF16,            BF16,      BF16>
@@ -72,7 +72,7 @@ using KernelTypes_KM_KN = ::testing::Types<
 
 using KernelTypes_KM_NK = ::testing::Types<
     //         ADataType, BDataType, ComputeDataType, CDataType
-#if defined(CK_ENABLE_FP8) 
+#if defined(CK_ENABLE_FP8)
     std::tuple<     BF16,        I4,            BF16,      BF16>,
 #endif
     std::tuple<     BF16,      BF16,            BF16,      BF16>
diff --git a/test/gemm_universal/test_gemm_universal_wmma_fp16.cpp b/test/gemm_universal/test_gemm_universal_wmma_fp16.cpp
index fa0220aa34..2f51253766 100644
--- a/test/gemm_universal/test_gemm_universal_wmma_fp16.cpp
+++ b/test/gemm_universal/test_gemm_universal_wmma_fp16.cpp
@@ -56,7 +56,7 @@ class TestGemmUniversal_FP16_KM_NK
 // clang-format off
 using KernelTypes_MK_KN = ::testing::Types<
     //         ADataType, BDataType, ComputeDataType, CDataType
-#if defined(CK_ENABLE_FP8) 
+#if defined(CK_ENABLE_FP8) && defined(CK_USE_WMMA_FP8)
     std::tuple<       F8,       F16,             F16,       F16>,
     std::tuple<      F16,        F8,             F16,       F16>,
 #endif
@@ -65,7 +65,7 @@ using KernelTypes_MK_KN = ::testing::Types<
 
 using KernelTypes_MK_NK = ::testing::Types<
     //         ADataType, BDataType, ComputeDataType, CDataType
-#if defined(CK_ENABLE_FP8) 
+#if defined(CK_ENABLE_FP8) && defined(CK_USE_WMMA_FP8)
     std::tuple<       F8,       F16,             F16,       F16>,
     std::tuple<      F16,        F8,             F16,       F16>,
     std::tuple<      F16,        I4,             F16,       F16>,
@@ -75,7 +75,7 @@ using KernelTypes_MK_NK = ::testing::Types<
 
 using KernelTypes_KM_NK = ::testing::Types<
     //         ADataType, BDataType, ComputeDataType, CDataType
-#if defined(CK_ENABLE_FP8) 
+#if defined(CK_ENABLE_FP8) && defined(CK_USE_WMMA_FP8)
     std::tuple<       F8,       F16,             F16,       F16>,
     std::tuple<      F16,        F8,             F16,       F16>,
     std::tuple<      F16,        I4,             F16,       F16>,
@@ -85,7 +85,7 @@ using KernelTypes_KM_NK = ::testing::Types<
 
 using KernelTypes_KM_KN = ::testing::Types<
     //         ADataType, BDataType, ComputeDataType, CDataType
-#if defined(CK_ENABLE_FP8) 
+#if defined(CK_ENABLE_FP8) && defined(CK_USE_WMMA_FP8)
     std::tuple<       F8,       F16,             F16,       F16>,
     std::tuple<      F16,        F8,             F16,       F16>,
 #endif
diff --git a/test/gemm_universal/test_gemm_universal_wmma_fp8.cpp b/test/gemm_universal/test_gemm_universal_wmma_fp8.cpp
index 3579424496..3484d49b93 100644
--- a/test/gemm_universal/test_gemm_universal_wmma_fp8.cpp
+++ b/test/gemm_universal/test_gemm_universal_wmma_fp8.cpp
@@ -7,7 +7,7 @@
 #include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
 #include "test_gemm_universal_util.hpp"
 
-#if CK_USE_WMMA_FP8
+#if defined(CK_USE_WMMA_FP8)
 
 using F8   = ck::f8_t;
 using BF16 = ck::bhalf_t;