mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
db4edea1e1
* Update TensorRT-LLM --------- Co-authored-by: Kota Tsuyuzaki <bloodeagle40234@gmail.com> Co-authored-by: Pzzzzz <hello-cd.plus@hotmail.com> Co-authored-by: Patrick Reiter Horn <patrick.horn@gmail.com>
34 lines
1.1 KiB
C++
34 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/common/assert.h"
|
|
#include "tensorrt_llm/common/cudaUtils.h"
|
|
|
|
namespace tensorrt_llm
|
|
{
|
|
namespace kernels
|
|
{
|
|
|
|
template <typename T>
|
|
void invokeBuildRelativeAttentionBias(T* relative_attention_bias, T const* relative_attention_bias_table,
|
|
int const head_num, int const seq_len, int const num_bucket, bool const is_bidirectional, int const max_distance,
|
|
cudaStream_t stream);
|
|
|
|
} // namespace kernels
|
|
} // namespace tensorrt_llm
|