diff --git a/example/ck_tile/03_gemm/run_gemm_example.inc b/example/ck_tile/03_gemm/run_gemm_example.inc
index f049e51f5e..fb67f944cc 100644
--- a/example/ck_tile/03_gemm/run_gemm_example.inc
+++ b/example/ck_tile/03_gemm/run_gemm_example.inc
@@ -215,10 +215,9 @@ auto shuffle_b(const ck_tile::HostTensor<T>& t)
             ck_tile::HostTensor<T> t_view({n_ / GemmConfig::N_Warp_Tile,
                                            GemmConfig::N_Warp_Tile,
                                            k_ / ItemsPerAccess,
-                                           1,
                                            ItemsPerAccess});
             std::copy(t.begin(), t.end(), t_view.begin());
-            return ck_tile::reference_permute(t_view, {0, 2, 3, 1, 4});
+            return ck_tile::reference_permute(t_view, {0, 2, 1, 3});
         }
     }
 }
diff --git a/include/ck_tile/ops/add_rmsnorm2d_rdquant.hpp b/include/ck_tile/ops/add_rmsnorm2d_rdquant.hpp
index 6c0972e10a..1768c802d5 100644
--- a/include/ck_tile/ops/add_rmsnorm2d_rdquant.hpp
+++ b/include/ck_tile/ops/add_rmsnorm2d_rdquant.hpp
@@ -9,7 +9,5 @@
 #include "ck_tile/ops/add_rmsnorm2d_rdquant/pipeline/add_rmsnorm2d_rdquant_fwd_pipeline_problem.hpp"
 #include "ck_tile/ops/add_rmsnorm2d_rdquant/pipeline/add_rmsnorm2d_rdquant_fwd_pipeline_three_pass.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/batched_transpose.hpp b/include/ck_tile/ops/batched_transpose.hpp
index 5822d7b91b..ca0088c812 100644
--- a/include/ck_tile/ops/batched_transpose.hpp
+++ b/include/ck_tile/ops/batched_transpose.hpp
@@ -12,7 +12,5 @@
 #include "ck_tile/ops/batched_transpose/pipeline/batched_transpose_policy.hpp"
 #include "ck_tile/ops/batched_transpose/pipeline/batched_transpose_problem.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/common.hpp b/include/ck_tile/ops/common.hpp
index eff2d625b3..027e2fdd94 100644
--- a/include/ck_tile/ops/common.hpp
+++ b/include/ck_tile/ops/common.hpp
@@ -4,7 +4,5 @@
 #pragma once
 
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/elementwise.hpp b/include/ck_tile/ops/elementwise.hpp
index 7f2303932e..4858245ec4 100644
--- a/include/ck_tile/ops/elementwise.hpp
+++ b/include/ck_tile/ops/elementwise.hpp
@@ -10,7 +10,5 @@
 #include "ck_tile/ops/elementwise/pipeline/elementwise_shape.hpp"
 #include "ck_tile/ops/elementwise/unary_element_wise_operation.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/epilogue.hpp b/include/ck_tile/ops/epilogue.hpp
index ec5a8ef445..6cc0fa8540 100644
--- a/include/ck_tile/ops/epilogue.hpp
+++ b/include/ck_tile/ops/epilogue.hpp
@@ -8,7 +8,5 @@
 #include "ck_tile/ops/epilogue/default_2d_epilogue.hpp"
 #include "ck_tile/ops/epilogue/dynamic_quant_epilogue.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/flatmm.hpp b/include/ck_tile/ops/flatmm.hpp
index 41463e6a2d..1714789e63 100644
--- a/include/ck_tile/ops/flatmm.hpp
+++ b/include/ck_tile/ops/flatmm.hpp
@@ -14,7 +14,5 @@
 #include "ck_tile/ops/flatmm/pipeline/flatmm_pipeline_agmem_bgmem_creg_v1_policy.hpp"
 #include "ck_tile/ops/flatmm/pipeline/tile_flatmm_shape.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/fmha.hpp b/include/ck_tile/ops/fmha.hpp
index 6b25c089bd..31de21a726 100644
--- a/include/ck_tile/ops/fmha.hpp
+++ b/include/ck_tile/ops/fmha.hpp
@@ -60,7 +60,5 @@
 #include "ck_tile/ops/fmha/pipeline/tile_fmha_shape.hpp"
 #include "ck_tile/ops/fmha/pipeline/tile_fmha_traits.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/fused_moe.hpp b/include/ck_tile/ops/fused_moe.hpp
index 71721f3408..ddb64a2189 100644
--- a/include/ck_tile/ops/fused_moe.hpp
+++ b/include/ck_tile/ops/fused_moe.hpp
@@ -16,7 +16,5 @@
 #include "ck_tile/ops/fused_moe/pipeline/moe_sorting_pipeline.hpp"
 #include "ck_tile/ops/fused_moe/pipeline/moe_sorting_policy.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/gemm.hpp b/include/ck_tile/ops/gemm.hpp
index c6f71dc399..4b412c6087 100644
--- a/include/ck_tile/ops/gemm.hpp
+++ b/include/ck_tile/ops/gemm.hpp
@@ -70,7 +70,5 @@
 #include "ck_tile/ops/gemm/warp/warp_gemm_smfmac_impl.hpp"
 #include "ck_tile/ops/gemm/warp/warp_wmma_gemm.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/gemm_quant.hpp b/include/ck_tile/ops/gemm_quant.hpp
index 478f348146..9f90050899 100644
--- a/include/ck_tile/ops/gemm_quant.hpp
+++ b/include/ck_tile/ops/gemm_quant.hpp
@@ -17,7 +17,5 @@
 #include "ck_tile/ops/gemm_quant/pipeline/gemm_quant_pipeline_problem.hpp"
 #include "ck_tile/ops/gemm_quant/pipeline/tile_gemm_quant_traits.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/grouped_convolution.hpp b/include/ck_tile/ops/grouped_convolution.hpp
index 1dd13b6246..09b50f26b0 100644
--- a/include/ck_tile/ops/grouped_convolution.hpp
+++ b/include/ck_tile/ops/grouped_convolution.hpp
@@ -12,7 +12,5 @@
 #include "ck_tile/ops/grouped_convolution/utils/transform_conv_bwd_weight_to_gemm.hpp"
 #include "ck_tile/ops/grouped_convolution/utils/transform_conv_fwd_to_gemm.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/image_to_column.hpp b/include/ck_tile/ops/image_to_column.hpp
index 2307b05190..93664ea138 100644
--- a/include/ck_tile/ops/image_to_column.hpp
+++ b/include/ck_tile/ops/image_to_column.hpp
@@ -7,7 +7,5 @@
 #include "ck_tile/ops/image_to_column/pipeline/block_image_to_column_problem.hpp"
 #include "ck_tile/ops/image_to_column/pipeline/tile_image_to_column_shape.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/layernorm2d.hpp b/include/ck_tile/ops/layernorm2d.hpp
index 9ce22137bf..afbb817db1 100644
--- a/include/ck_tile/ops/layernorm2d.hpp
+++ b/include/ck_tile/ops/layernorm2d.hpp
@@ -10,7 +10,5 @@
 #include "ck_tile/ops/layernorm2d/pipeline/layernorm2d_fwd_pipeline_two_pass.hpp"
 #include "ck_tile/ops/layernorm2d/pipeline/layernorm2d_fwd_traits.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/norm_reduce.hpp b/include/ck_tile/ops/norm_reduce.hpp
index aa074b7f9f..7dc3e8b7e7 100644
--- a/include/ck_tile/ops/norm_reduce.hpp
+++ b/include/ck_tile/ops/norm_reduce.hpp
@@ -7,7 +7,5 @@
 #include "ck_tile/ops/norm_reduce/block/block_norm_reduce_problem.hpp"
 #include "ck_tile/ops/norm_reduce/thread/thread_welford.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/permute.hpp b/include/ck_tile/ops/permute.hpp
index 46512c57fe..1cc3d9cbc3 100644
--- a/include/ck_tile/ops/permute.hpp
+++ b/include/ck_tile/ops/permute.hpp
@@ -6,7 +6,5 @@
 #include "ck_tile/ops/permute/kernel/generic_permute_kernel.hpp"
 #include "ck_tile/ops/permute/pipeline/generic_petmute_problem.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/reduce.hpp b/include/ck_tile/ops/reduce.hpp
index d628e9c945..a6721c9305 100644
--- a/include/ck_tile/ops/reduce.hpp
+++ b/include/ck_tile/ops/reduce.hpp
@@ -11,7 +11,5 @@
 #include "ck_tile/ops/reduce/pipeline/reduce2d_problem.hpp"
 #include "ck_tile/ops/reduce/pipeline/reduce2d_shape.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/rmsnorm2d.hpp b/include/ck_tile/ops/rmsnorm2d.hpp
index 00afcf4aed..610541b2e4 100644
--- a/include/ck_tile/ops/rmsnorm2d.hpp
+++ b/include/ck_tile/ops/rmsnorm2d.hpp
@@ -11,7 +11,5 @@
 #include "ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_pipeline_two_pass.hpp"
 #include "ck_tile/ops/rmsnorm2d/pipeline/rmsnorm2d_fwd_traits.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/smoothquant.hpp b/include/ck_tile/ops/smoothquant.hpp
index 1aa14c69e1..dc164dc1a0 100644
--- a/include/ck_tile/ops/smoothquant.hpp
+++ b/include/ck_tile/ops/smoothquant.hpp
@@ -10,7 +10,5 @@
 #include "ck_tile/ops/smoothquant/pipeline/smoothquant_pipeline_problem.hpp"
 #include "ck_tile/ops/smoothquant/pipeline/smoothquant_pipeline_two_pass.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/softmax.hpp b/include/ck_tile/ops/softmax.hpp
index d559dc15e2..b23e869d81 100644
--- a/include/ck_tile/ops/softmax.hpp
+++ b/include/ck_tile/ops/softmax.hpp
@@ -6,7 +6,5 @@
 #include "ck_tile/ops/softmax/block/block_softmax_2d.hpp"
 #include "ck_tile/ops/softmax/block/block_softmax_2d_problem.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/topk.hpp b/include/ck_tile/ops/topk.hpp
index 040c6b8ddc..1dc563f757 100644
--- a/include/ck_tile/ops/topk.hpp
+++ b/include/ck_tile/ops/topk.hpp
@@ -6,7 +6,5 @@
 #include "ck_tile/ops/topk/block/block_topk_stream_2d.hpp"
 #include "ck_tile/ops/topk/block/block_topk_stream_2d_problem.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"
diff --git a/include/ck_tile/ops/topk_softmax.hpp b/include/ck_tile/ops/topk_softmax.hpp
index d9657a9764..d0a810de4f 100644
--- a/include/ck_tile/ops/topk_softmax.hpp
+++ b/include/ck_tile/ops/topk_softmax.hpp
@@ -8,7 +8,5 @@
 #include "ck_tile/ops/topk_softmax/pipeline/topk_softmax_warp_per_row_policy.hpp"
 #include "ck_tile/ops/topk_softmax/pipeline/topk_softmax_warp_per_row_problem.hpp"
 #include "ck_tile/ops/common/generic_2d_block_shape.hpp"
-#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
-#include "ck_tile/ops/common/streamk_common.hpp"
 #include "ck_tile/ops/common/tensor_layout.hpp"
 #include "ck_tile/ops/common/utils.hpp"