TensorRT-LLMs/cpp/tensorrt_llm/pybind/runtime/generationOutput.cpp
Kaiyu Xie 6755a3f077
Update TensorRT-LLM (#422)
* Update TensorRT-LLM

---------

Co-authored-by: Tltin <TltinDeng01@gmail.com>
Co-authored-by: zhaohb <zhaohbcloud@126.com>
Co-authored-by: Bradley Heilbrun <brad@repl.it>
Co-authored-by: nqbao11 <nqbao11.01@gmail.com>
Co-authored-by: Nikhil Varghese <nikhil@bot-it.ai>
2023-11-18 00:05:54 +08:00

47 lines
1.6 KiB
C++

/*
* SPDX-FileCopyrightText: Copyright (c) 2022-2023 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 "generationOutput.h"
#include "tensorrt_llm/runtime/torch.h"
#include "tensorrt_llm/runtime/torchView.h"
namespace tr = tensorrt_llm::runtime;
using namespace tensorrt_llm::pybind::runtime;
std::shared_ptr<tr::GenerationOutput> GenerationOutput::toTrtLlm() const
{
auto output
= std::make_shared<tr::GenerationOutput>(tr::TorchView::of(ids.value()), tr::TorchView::of(lengths.value()));
if (logProbs)
{
output->logProbs = tr::TorchView::of(logProbs.value());
}
if (contextLogits)
{
output->contextLogits = tr::TorchView::of(contextLogits.value());
}
if (onTokenGenerated)
{
output->onTokenGenerated = [delegate = onTokenGenerated](
tr::GenerationOutput::TensorPtr const& ids, tr::SizeType step, bool finished)
{ delegate(tr::Torch::tensor(ids), step, finished); };
}
return output;
}