[LLM] First commit the llm deployment code

custom_ops/gpu_ops/common/cudaUtils.h

@@ -0,0 +1,33 @@
+// Copyright (c) 2024 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 <cuda_runtime.h>
+#include "paddle/phi/core/enforce.h"
+
+namespace common
+{
+
+inline int getSMVersion()
+{
+    int device{-1};
+    PADDLE_ENFORCE_GPU_SUCCESS(cudaGetDevice(&device));
+    int sm_major = 0;
+    int sm_minor = 0;
+    PADDLE_ENFORCE_GPU_SUCCESS(cudaDeviceGetAttribute(&sm_major, cudaDevAttrComputeCapabilityMajor, device));
+    PADDLE_ENFORCE_GPU_SUCCESS(cudaDeviceGetAttribute(&sm_minor, cudaDevAttrComputeCapabilityMinor, device));
+    return sm_major * 10 + sm_minor;
+}
+
+}