clean

include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_multi_abd_xdl_fixed_nk.hpp

@@ -123,7 +123,7 @@ __global__ void
         ignore = barrier_count_finished;
 
         GridwiseGemm::
-            template Run2<HasMainKBlockLoop, GemmSpec, AsLayout, BsLayout, DsLayout, ELayout>(
+            template Run<HasMainKBlockLoop, GemmSpec, AsLayout, BsLayout, DsLayout, ELayout>(
                 p_as_grid_,
                 p_bs_grid_,
                 p_ds_grid_,

include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_abd_xdl_cshuffle.hpp

@@ -956,7 +956,7 @@ struct GridwiseGemmMultipleABD_xdl_cshuffle
               typename DsLayout,
               typename ELayout,
               typename Block2ETileMap>
-    __device__ static void Run2(AsGridPointer p_as_grid,
+    __device__ static void Run(AsGridPointer p_as_grid,
                                BsGridPointer p_bs_grid,
                                DsGridPointer p_ds_grid,
                                void* __restrict__ p_e_grid_,