diff --git a/tests/tt_eager/python_api_testing/unit_testing/misc/test_transpose.py b/tests/tt_eager/python_api_testing/unit_testing/misc/test_transpose.py
index 4b51e48e761..6817fc1bd82 100644
--- a/tests/tt_eager/python_api_testing/unit_testing/misc/test_transpose.py
+++ b/tests/tt_eager/python_api_testing/unit_testing/misc/test_transpose.py
@@ -379,7 +379,7 @@ def run_tranpose_hw_rm_program_cache(device, n, c, h, w, use_program_cache):
 def test_tranpose_hw_rm_with_program_cache(device, n, c, h, w, use_program_cache):
     for _ in range(2):
         run_tranpose_hw_rm_program_cache(device, n, c, h, w, use_program_cache)
-        # # dummy tensor to change tensor alloc
+        # dummy tensor to change tensor alloc
         dummy_shape = [1, 1, 32, 32]
         py_dummy_tensor = torch.randn(dummy_shape)
         tt_dummy_tensor = ttnn.from_torch(
diff --git a/tests/ttnn/unit_tests/operations/test_permute.py b/tests/ttnn/unit_tests/operations/test_permute.py
index 2d919cd2af6..70e0fb4394d 100644
--- a/tests/ttnn/unit_tests/operations/test_permute.py
+++ b/tests/ttnn/unit_tests/operations/test_permute.py
@@ -247,7 +247,7 @@ def test_permute_squeeze(device):
 
 @pytest.mark.parametrize("shape", [(1, 49, 768)])
 @pytest.mark.parametrize("perm", generate_permutations(3))
-@pytest.mark.parametrize("layout", [ttnn.TILE_LAYOUT, ttnn.ROW_MAJOR_LAYOUT])
+@pytest.mark.parametrize("layout", [ttnn.TILE_LAYOUT])
 @pytest.mark.parametrize("memory_config", [ttnn.DRAM_MEMORY_CONFIG, ttnn.L1_MEMORY_CONFIG])
 @pytest.mark.parametrize("dtype", [ttnn.bfloat16, ttnn.float32])
 def test_permute_3D(shape, perm, layout, memory_config, dtype, device):
diff --git a/ttnn/cpp/ttnn/operations/data_movement/permute/device/kernels/compute/transpose_xh_rm_single_tile_size.cpp b/ttnn/cpp/ttnn/operations/data_movement/permute/device/kernels/compute/transpose_xw_rm_single_tile_size.cpp
similarity index 100%
rename from ttnn/cpp/ttnn/operations/data_movement/permute/device/kernels/compute/transpose_xh_rm_single_tile_size.cpp
rename to ttnn/cpp/ttnn/operations/data_movement/permute/device/kernels/compute/transpose_xw_rm_single_tile_size.cpp
diff --git a/ttnn/cpp/ttnn/operations/data_movement/permute/device/permute_program_factory.cpp b/ttnn/cpp/ttnn/operations/data_movement/permute/device/permute_program_factory.cpp
index 5ead48cb7cb..1a7a735d7e5 100644
--- a/ttnn/cpp/ttnn/operations/data_movement/permute/device/permute_program_factory.cpp
+++ b/ttnn/cpp/ttnn/operations/data_movement/permute/device/permute_program_factory.cpp
@@ -290,7 +290,7 @@ PermuteDeviceOperation::MultiCoreBlockedGeneric::create(
     bool fp32_dest_acc_en = cb_data_format_output == tt::DataFormat::Float32;
     auto compute_kernel_id = tt::tt_metal::CreateKernel(
         program,
-        "ttnn/cpp/ttnn/operations/data_movement/permute/device/kernels/compute/transpose_xh_rm_single_tile_size.cpp",
+        "ttnn/cpp/ttnn/operations/data_movement/permute/device/kernels/compute/transpose_xw_rm_single_tile_size.cpp",
         all_cores,
         tt::tt_metal::ComputeConfig{
             .fp32_dest_acc_en = fp32_dest_acc_en,