mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
d31fefde2c
* chore: Remove GptSession/V1 from TRT workflow Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove stateful decoders Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove GptSession buffers Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove GptSession utils Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove GptSession kernels Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove V1 GPT models from tests Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove gptSessionBenchmark from scripts and docs Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove gptSession IO classes Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove GptSession from test lists Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove GptSession from docs Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove useless encoder test Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove mActualBatchSize from DecoderState Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: Remove static batching from ExecutorTest - Updated `validateContextLogits` and `validateGenerationLogits` functions to remove the `batchingType` parameter. - Adjusted related test functions to reflect the changes in parameter lists. - Cleaned up the instantiation of test cases to eliminate unnecessary batchingType references. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> --------- Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>
79 lines
2.7 KiB
C++
79 lines
2.7 KiB
C++
/*
|
|
* 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.
|
|
*/
|
|
|
|
#include "rnnStateBuffers.h"
|
|
|
|
#include "tensorrt_llm/batch_manager/llmRequest.h"
|
|
#include "tensorrt_llm/batch_manager/rnnStateManager.h"
|
|
#include "tensorrt_llm/batch_manager/runtimeBuffers.h"
|
|
#include "tensorrt_llm/common/nvtxUtils.h"
|
|
#include "tensorrt_llm/runtime/tllmRuntime.h"
|
|
|
|
using namespace tensorrt_llm::runtime;
|
|
|
|
namespace tensorrt_llm::batch_manager
|
|
{
|
|
|
|
RnnStateBuffers::RnnStateBuffers(SizeType32 maxBatchSize, runtime::TllmRuntime const& runtime)
|
|
{
|
|
auto const& manager = runtime.getBufferManager();
|
|
|
|
slotMappingHost = BufferManager::cpu(ITensor::makeShape({maxBatchSize}), nvinfer1::DataType::kINT32);
|
|
slotMappingDevice = manager.gpu(ITensor::makeShape({maxBatchSize}), nvinfer1::DataType::kINT32);
|
|
}
|
|
|
|
void RnnStateBuffers::reshape(SizeType32 numSequences)
|
|
{
|
|
slotMappingHost->reshape(ITensor::makeShape({numSequences}));
|
|
slotMappingDevice->reshape(ITensor::makeShape({numSequences}));
|
|
}
|
|
|
|
void RnnStateBuffers::fillSlotMappings(
|
|
RequestVector const& contextRequests, rnn_state_manager::RnnStateManager* rnnStateManager)
|
|
{
|
|
TLLM_LOG_TRACE("%s start", __PRETTY_FUNCTION__);
|
|
NVTX3_SCOPED_RANGE(rnnStateBuffersFillSlotMappings);
|
|
|
|
SizeType32 batchIdx{0};
|
|
for (auto const& llmReq : contextRequests)
|
|
{
|
|
auto const seqSlot = llmReq->mSeqSlot.value();
|
|
auto const reqBeamWidth = llmReq->mSamplingConfig.beamWidth;
|
|
rnnStateManager->fillSlotMapping(*slotMappingHost, batchIdx, seqSlot, reqBeamWidth);
|
|
++batchIdx;
|
|
}
|
|
TLLM_LOG_TRACE("%s stop", __PRETTY_FUNCTION__);
|
|
}
|
|
|
|
void RnnStateBuffers::copySlotMappingH2D(runtime::TllmRuntime const& runtime)
|
|
{
|
|
auto const& manager = runtime.getBufferManager();
|
|
manager.copy(*slotMappingHost, *slotMappingDevice);
|
|
}
|
|
|
|
void RnnStateBuffers::getBuffers(TensorMap& inputBuffers) const
|
|
{
|
|
TLLM_LOG_TRACE("%s start", __PRETTY_FUNCTION__);
|
|
NVTX3_SCOPED_RANGE(rnnStateBuffersGetBuffers);
|
|
|
|
inputBuffers.insert_or_assign("slot_mapping", slotMappingDevice);
|
|
|
|
TLLM_LOG_TRACE("%s stop", __PRETTY_FUNCTION__);
|
|
}
|
|
|
|
} // namespace tensorrt_llm::batch_manager
|