mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
711a28d9bf
* Update TensorRT-LLM --------- Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
38 lines
1.3 KiB
C++
38 lines
1.3 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 "inferenceRequest.h"
|
|
|
|
#include "tensorrt_llm/batch_manager/inferenceRequest.h"
|
|
#include "tensorrt_llm/runtime/torchView.h"
|
|
#include <memory>
|
|
|
|
namespace tb = tensorrt_llm::batch_manager;
|
|
namespace tr = tensorrt_llm::runtime;
|
|
|
|
using namespace tensorrt_llm::pybind::batch_manager;
|
|
|
|
std::shared_ptr<tb::InferenceRequest> InferenceRequest::toTrtLlm() const
|
|
{
|
|
tb::InferenceRequest::TensorMap trtTensors;
|
|
for (const auto& torchTensorItem : mInputTensors)
|
|
{
|
|
trtTensors.insert({torchTensorItem.first, tr::TorchView::of(torchTensorItem.second)});
|
|
}
|
|
|
|
return std::make_shared<tb::InferenceRequest>(trtTensors, mRequestId);
|
|
}
|