CUDA Kernel No.14】fused_transpose_wlch_split_quant算子Kernel修复 (PaddlePaddle#2012)

Co-authored-by: Tao Luo <luotao02@baidu.com>
Co-authored-by: Yuqiang Ge <143453447+YqGe585@users.noreply.github.com>

Author: 3 people

backends/iluvatar_gpu/kernels/cuda_kernels/fused_transpose_wlch_split_quant_kernel_register.cu

@@ -13,7 +13,7 @@
 // limitations under the License.
 
 #include "paddle/phi/core/kernel_registry.h"
-#include "paddle/phi/kernels/fusion/gpu/fused_transpose_wlch_split_quant_kernel.cu"  //NOLINT
+#include "paddle/phi/kernels/fusion/gpu/fused_transpose_wlch_split_quant_kernel.h"
 #include "paddle/phi/kernels/fusion/gpu/quant_utils.h"
 #include "paddle/phi/kernels/primitive/datamover_primitives.h"
 

backends/metax_gpu/kernels/fusion/fused_transpose_wlch_split_quant_kernel_register.cu

@@ -13,7 +13,7 @@
 // limitations under the License.
 
 #include "paddle/phi/core/kernel_registry.h"
-#include "paddle/phi/kernels/fusion/gpu/fused_transpose_wlch_split_quant_kernel.cu"  //NOLINT
+#include "paddle/phi/kernels/fusion/gpu/fused_transpose_wlch_split_quant_kernel.h"
 #include "paddle/phi/kernels/fusion/gpu/quant_utils.h"
 #include "paddle/phi/kernels/primitive/datamover_primitives.h"