fixed

include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3.hpp

@@ -1757,7 +1757,7 @@ struct GridwiseGemm_xdl_cshuffle_v3
 
         auto b_block_buf_ping = make_dynamic_buffer<AddressSpaceEnum::Lds>(
             bit_cast<BDataType*>(static_cast<char*>(p_shared_0) +
-                                    a_block_space_size_aligned * sizeof(ADataType)),
+                                 a_block_space_size_aligned * sizeof(ADataType)),
             b_block_desc_bk0_n_bk1.GetElementSpaceSize());
 
         auto a_block_buf_pong = make_dynamic_buffer<AddressSpaceEnum::Lds>(

include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp

@@ -381,8 +381,8 @@ struct ThreadwiseTensorSliceTransfer_v3r1
                       (is_same<f8_t, remove_cvref_t<DstData>>::value &&
                        SrcScalarPerVector % 4 == 0 && DstScalarPerVector % 4 == 0)))
         {
-            //static_assert(is_same_v<remove_cvref_t<SrcData>, pk_i4_t>,
-                          //"transpose is not allowed for pk_i4_t");
+            // static_assert(is_same_v<remove_cvref_t<SrcData>, pk_i4_t>,
+            //"transpose is not allowed for pk_i4_t");
 #if 1
             // each transpose does
             // DstScalarPerVector # of src vectors in src_thread_scratch_