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 5d9da7d4da..ace8f00cb9 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
@@ -224,21 +224,41 @@ struct DeviceOperationInstanceFactory<
                          is_same_v<CLayout, Row>)
             {
                 add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_default_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
+                    op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Row> && is_same_v<BLayout, Col> &&
                               is_same_v<CLayout, Row>)
             {
                 add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_default_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
+                    op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Row> &&
                               is_same_v<CLayout, Row>)
             {
                 add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_default_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_kpadding_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnkpadding_instances(
+                    op_ptrs);
             }
             else if constexpr(is_same_v<ALayout, Col> && is_same_v<BLayout, Col> &&
                               is_same_v<CLayout, Row>)
             {
                 add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_default_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_kpadding_instances(op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnpadding_instances(
+                    op_ptrs);
+                add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnkpadding_instances(
+                    op_ptrs);
             }
         }
 
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 dcf152477b..18da3a21a2 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
@@ -229,21 +229,69 @@ 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>>>&
         instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
 
 void add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
 
 void add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
 
 void add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_default_instances(
     std::vector<std::unique_ptr<
         DeviceGemmV2<Col, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
         instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
+void add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances);
 
 void add_device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_default_instances(
     std::vector<std::unique_ptr<
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt b/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt
index 1668d0f27f..f70b53d455 100644
--- a/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/CMakeLists.txt
@@ -56,9 +56,24 @@ list(APPEND GEMM_UNIVERSAL_INSTANCES
         device_gemm_wmma_universal_f16_i4_f16/device_gemm_wmma_universal_f16_i4_f16_km_nk_mn_comp_default_instance.cpp
 
         device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_default_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp
+
         device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_default_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
+
         device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_default_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_kpadding_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp
+
         device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_default_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_kpadding_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp
+        device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp
         
         device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_default_instance.cpp
         device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_default_instance.cpp
@@ -176,9 +191,24 @@ set_source_files_properties(device_gemm_wmma_universal_f16_i4_bf16/device_gemm_w
 set_source_files_properties(device_gemm_wmma_universal_f16_i4_bf16/device_gemm_wmma_universal_f16_i4_bf16_km_nk_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
 
 set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+
 set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+
 set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+
 set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_kpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
+set_source_files_properties(device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
 
 set_source_files_properties(device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_kn_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
 set_source_files_properties(device_gemm_wmma_universal_f16_f8_f16/device_gemm_wmma_universal_f16_f8_f16_mk_nk_mn_comp_default_instance.cpp PROPERTIES COMPILE_OPTIONS ";-mllvm;-greedy-reverse-local-assignment=1")
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_kpadding_instance.cpp
new file mode 100644
index 0000000000..dbbcba041a
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_kpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_km_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_instances<GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp
new file mode 100644
index 0000000000..f6d39ed91f
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnkpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_km_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_instances<GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp
new file mode 100644
index 0000000000..8c34c5d447
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_km_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_km_kn_mn_comp_instances<GemmMNPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_kpadding_instance.cpp
new file mode 100644
index 0000000000..fc1fab401f
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_kpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_km_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_instances<GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp
new file mode 100644
index 0000000000..1cc7de8813
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnkpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_km_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_instances<GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp
new file mode 100644
index 0000000000..a4db6f085b
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_km_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Col, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_km_nk_mn_comp_instances<GemmMNPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp
new file mode 100644
index 0000000000..34053e860e
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_instances<GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp
new file mode 100644
index 0000000000..db1c60967c
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnkpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_instances<GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp
new file mode 100644
index 0000000000..fa84694eb7
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Row, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_mk_kn_mn_comp_instances<GemmMNPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
new file mode 100644
index 0000000000..c4d75b0c23
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_kpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_instances<GemmKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
new file mode 100644
index 0000000000..b722bd32c1
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnkpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_instances<GemmMNKPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck
diff --git a/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
new file mode 100644
index 0000000000..3638fa33ea
--- /dev/null
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal/device_gemm_wmma_universal_f8_f16_f16/device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instance.cpp
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
+
+#include "device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn.hpp"
+#include "ck/host_utility/device_prop.hpp"
+
+namespace ck {
+namespace tensor_operation {
+namespace device {
+namespace instance {
+
+void add_device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_mnpadding_instances(
+    std::vector<std::unique_ptr<
+        DeviceGemmV2<Row, Col, Row, F8, F16, F16, PassThrough, PassThrough, PassThrough>>>&
+        instances)
+{
+    add_device_operation_instances(
+        instances, device_gemm_wmma_universal_f8_f16_f16_mk_nk_mn_comp_instances<GemmMNPadding>{});
+}
+
+} // namespace instance
+} // namespace device
+} // namespace tensor_operation
+} // namespace ck