mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-23 20:23:08 +08:00
37 lines
1.2 KiB
C++
37 lines
1.2 KiB
C++
/*
|
|
* Copyright (c) 2020-2023, 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 "cubin/kernelMetaInfo.h"
|
|
#include "fmhaRunnerParams.h"
|
|
#include "kernelParams.h"
|
|
|
|
namespace tensorrt_llm
|
|
{
|
|
namespace kernels
|
|
{
|
|
|
|
////////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
void runFmhaReduction(TllmGenFmhaKernelMetaInfo const& kernelMeta, KernelParams const& params,
|
|
int32_t multiProcessorCount, cudaStream_t stream);
|
|
|
|
////////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
} // namespace kernels
|
|
} // namespace tensorrt_llm
|