diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p1_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p1_padding.cpp
index 618f763c60..da74069c72 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p1_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p1_padding.cpp
@@ -24,7 +24,12 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16
     add_device_operation_instances(
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p1<
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p1<
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p2_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p2_padding.cpp
index 60627770a4..59487f1fc1 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p2_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p2_padding.cpp
@@ -24,7 +24,12 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16
     add_device_operation_instances(
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p2<
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p2<
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p3_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p3_padding.cpp
index 78ae66df23..6dea50b0d7 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p3_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p3_padding.cpp
@@ -24,7 +24,12 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16
     add_device_operation_instances(
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p3<
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p3<
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p4_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p4_padding.cpp
index b067402fe5..23f2d7e544 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p4_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p4_padding.cpp
@@ -24,7 +24,12 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16
     add_device_operation_instances(
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p4<
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p4<
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p5_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p5_padding.cpp
index 564de1e3be..f428444d6e 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p5_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p5_padding.cpp
@@ -24,7 +24,12 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16
     add_device_operation_instances(
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p5<
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p5<
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p6_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p6_padding.cpp
index c535d59912..0037b7699d 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p6_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_default_instance_p6_padding.cpp
@@ -24,7 +24,12 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16
     add_device_operation_instances(
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p6<
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma16x16_mn_compute_instances_p6<
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn.hpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn.hpp
index 274e1ca302..56fc37fc4d 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn.hpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn.hpp
@@ -28,6 +28,7 @@ using MultiplyMultiply = element_wise::MultiplyMultiply;
 
 static constexpr auto GemmDefault    = GemmSpecialization::Default;
 static constexpr auto GemmKPadding   = GemmSpecialization::KPadding;
+static constexpr auto GemmNPadding   = GemmSpecialization::NPadding;
 static constexpr auto GemmNKPadding  = GemmSpecialization::NKPadding;
 static constexpr auto GemmMNPadding  = GemmSpecialization::MNPadding;
 static constexpr auto GemmMNKPadding = GemmSpecialization::MNKPadding;
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_compute_default_instance_p1_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_compute_default_instance_p1_padding.cpp
index df5d426888..a5cb29e8aa 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_compute_default_instance_p1_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_compute_default_instance_p1_padding.cpp
@@ -24,7 +24,12 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
     add_device_operation_instances(
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_compute_instances_p1<
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_compute_instances_p1<
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_compute_default_instance_p2_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_compute_default_instance_p2_padding.cpp
index 0eaee05902..99e48992ee 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_compute_default_instance_p2_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_compute_default_instance_p2_padding.cpp
@@ -24,7 +24,12 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
     add_device_operation_instances(
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_compute_instances_p2<
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_compute_instances_p2<
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p1_default_instance_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p1_default_instance_padding.cpp
index fa79edc6c7..e19755a90b 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p1_default_instance_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p1_default_instance_padding.cpp
@@ -25,7 +25,12 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p1_instances<
             v2,
-            GemmNKPadding>{});
+            GemmNPadding>{});
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p1_instances<
+            v2,
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p1_default_instance_v2_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p1_default_instance_v2_padding.cpp
index 941974fb07..3577006bc6 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p1_default_instance_v2_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p1_default_instance_v2_padding.cpp
@@ -25,7 +25,13 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p1_instances<
             v1,
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p1_instances<
+            v1,
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p2_default_instance_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p2_default_instance_padding.cpp
index 057ef9e74c..c0b39001aa 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p2_default_instance_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p2_default_instance_padding.cpp
@@ -25,7 +25,13 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p2_instances<
             v1,
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p2_instances<
+            v1,
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p2_default_instance_v2_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p2_default_instance_v2_padding.cpp
index 5d76846bfe..0ea3a47d50 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p2_default_instance_v2_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p2_default_instance_v2_padding.cpp
@@ -25,7 +25,13 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p2_instances<
             v2,
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p2_instances<
+            v2,
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p3_default_instance_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p3_default_instance_padding.cpp
index 36fa8047e5..ef28052b3a 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p3_default_instance_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p3_default_instance_padding.cpp
@@ -25,7 +25,13 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p3_instances<
             v1,
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p3_instances<
+            v1,
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p3_default_instance_v2_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p3_default_instance_v2_padding.cpp
index d45f2c065c..144b2b2c93 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p3_default_instance_v2_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p3_default_instance_v2_padding.cpp
@@ -25,7 +25,13 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p3_instances<
             v2,
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p3_instances<
+            v2,
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p4_default_instance_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p4_default_instance_padding.cpp
index d9cb2d7f73..00408470d5 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p4_default_instance_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p4_default_instance_padding.cpp
@@ -25,7 +25,13 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p4_instances<
             v1,
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p4_instances<
+            v1,
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p4_default_instance_v2_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p4_default_instance_v2_padding.cpp
index df092f915b..cb9b4dfca7 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p4_default_instance_v2_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p4_default_instance_v2_padding.cpp
@@ -25,7 +25,13 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p4_instances<
             v2,
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p4_instances<
+            v2,
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p5_default_instance_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p5_default_instance_padding.cpp
index cd72790a07..65e0ef9e83 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p5_default_instance_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p5_default_instance_padding.cpp
@@ -25,7 +25,13 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p5_instances<
             v1,
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p5_instances<
+            v1,
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p5_default_instance_v2_padding.cpp b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p5_default_instance_v2_padding.cpp
index 666f14342d..612dbad47c 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p5_default_instance_v2_padding.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multiply_multiply_wp/f8_f8_f16/device_gemm_multiply_multiply_wp_xdl_f8_f8_f16_mk_mfma_mn_p5_default_instance_v2_padding.cpp
@@ -25,7 +25,13 @@ void add_device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_m
         instances,
         device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p5_instances<
             v2,
-            GemmNKPadding>{});
+            GemmNPadding>{});
+
+    add_device_operation_instances(
+        instances,
+        device_gemm_multiply_multiply_weight_preshuffle_xdl_f8_f8_f16_mk_mfma_mn_p5_instances<
+            v2,
+            GemmKPadding>{});
 }
 
 } // namespace instance
diff --git a/profiler/include/profiler/profile_gemm_multiply_multiply_wp_impl.hpp b/profiler/include/profiler/profile_gemm_multiply_multiply_wp_impl.hpp
index f33a38de28..16cc2df3ec 100644
--- a/profiler/include/profiler/profile_gemm_multiply_multiply_wp_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_multiply_multiply_wp_impl.hpp
@@ -118,7 +118,7 @@ bool profile_gemm_multiply_multiply_weight_preshuffle_impl(int do_verification,
 
     if(bKPadding && bNPadding)
     {
-        std::cout << "Not support N and K both Paddding!" << std::endl;
+        std::cout << "Not support N and K both paddding!" << std::endl;
         return true;
     }
     Tensor<ADataType> a_m_k(f_host_tensor_descriptor(M, K, StrideA, ALayout{}));