/*
 * Copyright (c) 2022-2024, NVIDIA CORPORATION.  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 "tensorrt_llm/runtime/modelConfig.h"
#include "tensorrt_llm/runtime/worldConfig.h"

#include <cstdint>
#include <string>
#include <vector>

namespace tensorrt_llm::runtime
{
class TllmRuntime;

namespace utils
{

int initDevice(WorldConfig const& worldConfig);

std::vector<uint8_t> loadEngine(std::string const& enginePath);

void insertTensorVector(StringPtrMap<ITensor>& map, std::string const& key, std::vector<ITensor::SharedPtr> const& vec,
    SizeType32 indexOffset, std::vector<ModelConfig::LayerType> const& layerTypes, ModelConfig::LayerType type);

void insertTensorSlices(
    StringPtrMap<ITensor>& map, std::string const& key, ITensor::SharedPtr const& tensor, SizeType32 indexOffset);

} // namespace utils
} // namespace tensorrt_llm::runtime