mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
72057a0a64
* disable overlap in encoder Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: invokeGatherBatch Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: overlap same batch Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: add enableTrtOverlap to ExecutorConfig Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * disable overlap for beam search and spec decode Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * skip overlap tests with beam search or speculative decoding Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * moveFinishedContextRequestsToGeneration and skip unfinished requests in updateRequests Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * enable overlap in GptChunkedLongContextTests Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: Enable overlap in gptManagerBenchmark Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: Improve early exit Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: Use OptionalRef for newOutputTokens tensor Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: Add overlap scheduling support to TRTLLMDecoder - Updated TRTLLMDecoder to accept an `enable_overlap_scheduler` parameter. - Modified the decoder's internal logic to utilize the overlap scheduling feature. - Adjusted the sequence lengths handling to ensure compatibility with the new scheduling approach. - Enhanced unit tests to include cases for the overlap scheduler with the TRTLLMDecoder. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * fix: allNewTokens in PP Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> --------- Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
68 lines
2.6 KiB
C++
68 lines
2.6 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/common.h"
|
|
#include "tensorrt_llm/runtime/iGptDecoderBatched.h"
|
|
#include "tensorrt_llm/runtime/modelConfig.h"
|
|
|
|
namespace tensorrt_llm::batch_manager
|
|
{
|
|
class DecoderInputBuffers;
|
|
class DecoderBuffers;
|
|
class RuntimeBuffers;
|
|
} // namespace tensorrt_llm::batch_manager
|
|
|
|
namespace tensorrt_llm::runtime::decoder
|
|
{
|
|
class DecoderState;
|
|
} // namespace tensorrt_llm::runtime::decoder
|
|
|
|
namespace tensorrt_llm::batch_manager
|
|
{
|
|
class MakeDecodingBatchInputOutput : Algorithm
|
|
{
|
|
public:
|
|
template <typename T>
|
|
using OptionalRef = tensorrt_llm::common::OptionalRef<T>;
|
|
|
|
constexpr static auto name{"MakeDecodingBatchInputOutput"};
|
|
|
|
using SizeType32 = tensorrt_llm::runtime::SizeType32;
|
|
using TensorPtr = runtime::decoder_batch::Input::TensorPtr;
|
|
|
|
MakeDecodingBatchInputOutput() = default;
|
|
|
|
std::tuple<std::unique_ptr<runtime::decoder_batch::Input>, std::unique_ptr<runtime::decoder_batch::Output>>
|
|
operator()(RequestVector const& contextRequests, RequestVector const& generationRequests,
|
|
DecoderBuffers& decoderBuffers, DecoderInputBuffers const& inputBuffers,
|
|
runtime::decoder::DecoderState& decoderState, runtime::ModelConfig const& modelConfig,
|
|
SizeType32 maxNumSequences, SizeType32 beamWidth, bool isTrtOverlap, runtime::BufferManager const& manager,
|
|
runtime::CudaStream const& stream, OptionalRef<RuntimeBuffers> fusedRuntimeBuffers) const;
|
|
|
|
[[nodiscard]] static std::unique_ptr<runtime::decoder_batch::Input> createDecoderBatchInputs(
|
|
std::vector<SizeType32> const& activeSlots, runtime::decoder::DecoderState const& decoderState,
|
|
std::vector<TensorPtr> const& logits, SizeType32 maxNumSequences, std::vector<TensorPtr> const& batchSlots,
|
|
TensorPtr const& cacheIndirectionInput);
|
|
};
|
|
|
|
} // namespace tensorrt_llm::batch_manager
|