mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
56 lines
1.7 KiB
C++
56 lines
1.7 KiB
C++
/*
|
|
* SPDX-FileCopyrightText: Copyright (c) 2022-2024 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 "common.h"
|
|
#include "tensorrt_llm/common/algorithm.h"
|
|
#include "tensorrt_llm/common/optionalRef.h"
|
|
#include "tensorrt_llm/runtime/modelConfig.h"
|
|
|
|
namespace tensorrt_llm::runtime
|
|
{
|
|
class BufferManager;
|
|
} // namespace tensorrt_llm::runtime
|
|
|
|
namespace tensorrt_llm::batch_manager
|
|
{
|
|
|
|
class DecoderInputBuffers;
|
|
class DraftBuffers;
|
|
class RuntimeBuffers;
|
|
|
|
namespace tr = tensorrt_llm::runtime;
|
|
|
|
class HandleGenerationLogits : Algorithm
|
|
{
|
|
public:
|
|
template <typename T>
|
|
using OptionalRef = tensorrt_llm::common::OptionalRef<T>;
|
|
|
|
constexpr static auto name{"HandleGenerationLogits"};
|
|
|
|
HandleGenerationLogits() = default;
|
|
|
|
void operator()(DecoderInputBuffers& inputBuffers, RequestVector const& generationRequests,
|
|
tr::ITensor::SharedPtr const& logits, tr::SizeType32 logitsIndex, tr::ModelConfig const& modelConfig,
|
|
tr::BufferManager const& manager, OptionalRef<RuntimeBuffers> genRuntimeBuffers,
|
|
OptionalRef<DraftBuffers> draftBuffers) const;
|
|
};
|
|
|
|
} // namespace tensorrt_llm::batch_manager
|