/*
 * SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 * SPDX-License-Identifier: Apache-2.0
 *
 * 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/batch_manager/common.h"
#include "tensorrt_llm/runtime/iTensor.h"

namespace tensorrt_llm::runtime
{
class TllmRuntime;
} // namespace tensorrt_llm::runtime

namespace tensorrt_llm::batch_manager
{

namespace rnn_state_manager
{
class RnnStateManager;
}

class RnnStateBuffers
{
public:
    using SizeType32 = tensorrt_llm::runtime::SizeType32;
    using TensorPtr = runtime::ITensor::SharedPtr;
    using TensorMap = runtime::StringPtrMap<runtime::ITensor>;

    // others should be in rnnStateManager, we only need slotMapping here.
    TensorPtr slotMappingHost;   // [batch_size]
    TensorPtr slotMappingDevice; // [batch_size]

    RnnStateBuffers(SizeType32 maxBatchSize, runtime::TllmRuntime const& runtime);

    void reshape(SizeType32 numSequences);

    void fillSlotMappings(RequestVector const& contextRequests, rnn_state_manager::RnnStateManager* rnnStateManager);

    void copySlotMappingH2D(runtime::TllmRuntime const& runtime);

    void getBuffers(TensorMap& inputBuffers) const;
};

} // namespace tensorrt_llm::batch_manager