【CUDA Kernel No.18】skip_layernorm算子Kernel修复 -part (#75542)

* 【CUDA Kernel No.18】skip_layernorm算子Kernel修复 -part

* fix 仅在gpu中发现此kernel，把头文件和kernel实现放在同级目录下

Author: SpongeBob0318

paddle/phi/kernels/fusion/gpu/skip_layernorm_kernel.cu

@@ -12,6 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+#include "paddle/phi/kernels/fusion/gpu/skip_layernorm_kernel.h"
 #include "paddle/common/errors.h"
 #include "paddle/phi/core/kernel_registry.h"
 #include "paddle/phi/core/tensor_utils.h"

paddle/phi/kernels/fusion/gpu/skip_layernorm_kernel.h

@@ -0,0 +1,34 @@
+// Copyright (c) 2023 PaddlePaddle Authors. All Rights Reserved.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+#pragma once
+
+#include "paddle/phi/core/dense_tensor.h"
+#include "paddle/phi/core/kernel_registry.h"
+
+namespace phi {
+namespace fusion {
+
+template <typename T, typename Context>
+void SkipLayerNormKernel(const Context& dev_ctx,
+                         const DenseTensor& x,
+                         const DenseTensor& y,
+                         const DenseTensor& scale,
+                         const DenseTensor& bias,
+                         const float epsilon,
+                         const int begin_norm_axis,
+                         DenseTensor* out);
+
+}  // namespace fusion
+}  // namespace phi