mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
bca9a33b02
* Update TensorRT-LLM --------- Co-authored-by: Timur Abishev <abishev.timur@gmail.com> Co-authored-by: MahmoudAshraf97 <hassouna97.ma@gmail.com> Co-authored-by: Saeyoon Oh <saeyoon.oh@furiosa.ai> Co-authored-by: hattizai <hattizai@gmail.com>
35 lines
1.1 KiB
C++
35 lines
1.1 KiB
C++
/*
|
|
* Copyright (c) 2022-2024, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* 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 "tensorrt_llm/runtime/bufferManager.h"
|
|
#include "tensorrt_llm/runtime/iTensor.h"
|
|
|
|
#include <string>
|
|
|
|
namespace tensorrt_llm::runtime::utils
|
|
{
|
|
|
|
//! \brief Create new tensor from numpy file.
|
|
[[nodiscard]] ITensor::UniquePtr loadNpy(
|
|
BufferManager const& manager, std::string const& npyFile, const MemoryType where);
|
|
|
|
//! \brief Save tensor to numpy file.
|
|
void saveNpy(BufferManager const& manager, ITensor const& tensor, std::string const& filename);
|
|
|
|
} // namespace tensorrt_llm::runtime::utils
|