mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
39 lines
1.2 KiB
C++
39 lines
1.2 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/common.h"
|
|
|
|
namespace tensorrt_llm::runtime
|
|
{
|
|
struct RuntimeDefaults
|
|
{
|
|
RuntimeDefaults(
|
|
std::optional<std::vector<SizeType32>> maxAttentionWindowVec, std::optional<SizeType32> sinkTokenLength)
|
|
: maxAttentionWindowVec(maxAttentionWindowVec)
|
|
, sinkTokenLength(sinkTokenLength)
|
|
{
|
|
}
|
|
|
|
std::optional<std::vector<SizeType32>> maxAttentionWindowVec;
|
|
std::optional<SizeType32> sinkTokenLength;
|
|
|
|
RuntimeDefaults() = default;
|
|
};
|
|
|
|
} // namespace tensorrt_llm::runtime
|