[LLM] First commit the llm deployment code

custom_ops/gpu_ops/speculate_decoding/speculate_msg.h

@@ -0,0 +1,32 @@
+// 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 <stdio.h>
+#include <string.h>
+#include <sys/ipc.h>
+#include <sys/msg.h>
+#include <sys/types.h>
+#include "paddle/extension.h"
+
+#define MAX_BSZ 256
+#define MAX_DRAFT_TOKENS 6
+
+// TODO: replace all msgdata in speculate-decoding
+struct speculate_msgdata {
+    long mtype;
+    int mtext[MAX_BSZ * MAX_DRAFT_TOKENS + MAX_BSZ +
+              2];  // stop_flag, bsz, tokens
+};