fix instance

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instance.cpp

@@ -9,8 +9,9 @@ namespace device {
 namespace instance {
 
 void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnkpadding_instances(
-    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>& 
-    instances)
+    std::vector<std::unique_ptr<
+        DeviceGemm_Streamk_V2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>& 
+        instances)
 {
     add_device_operation_instances(
         instances, device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_instances<GemmMNKPadding>{});

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instance.cpp

@@ -9,15 +9,9 @@ namespace device {
 namespace instance {
 
 void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_km_kn_mn_comp_mnpadding_instances(
-    std::vector<std::unique_ptr<DeviceGemm_Streamk_V2<Col,
-                                                      Row,
-                                                      Row,
-                                                      BF16,
-                                                      BF16,
-                                                      BF16,
-                                                      PassThrough,
-                                                      PassThrough,
-                                                      PassThrough>>>& instances)
+    std::vector<std::unique_ptr<
+    DeviceGemm_Streamk_V2<Col, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough,PassThrough>>>& 
+    instances)
 {
     add_device_operation_instances(
         instances,

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_kpadding_instance.cpp

@@ -10,7 +10,7 @@ namespace instance {
 
 void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_kpadding_instances(
     std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
+        DeviceGemm_Streamk_V2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances)
 {
     add_device_operation_instances(

library/src/tensor_operation_instance/gpu/gemm_universal_streamk/device_gemm_xdl_universal_streamk_bf16_bf16_bf16/device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_mnkpadding_instance.cpp

@@ -10,7 +10,7 @@ namespace instance {
 
 void add_device_gemm_xdl_universal_streamk_bf16_bf16_bf16_mk_kn_mn_mem_v2_mnkpadding_instances(
     std::vector<std::unique_ptr<
-        DeviceGemmV2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
+        DeviceGemm_Streamk_V2<Row, Row, Row, BF16, BF16, BF16, PassThrough, PassThrough, PassThrough>>>&
         instances)
 {
     add_device_operation_instances(