mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
b99c5ce8c1
Signed-off-by: yunruis <yunruis@nvidia.com> Signed-off-by: kduan <176893526+Kefeng-Duan@users.noreply.github.com> Signed-off-by: Kefeng-Duan <176893526+Kefeng-Duan@users.noreply.github.com> Co-authored-by: kduan <176893526+Kefeng-Duan@users.noreply.github.com>
31 lines
1.0 KiB
C++
31 lines
1.0 KiB
C++
/*
|
|
* Copyright (c) 2019-2023, 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 "tensorrt_llm/common/cudaUtils.h"
|
|
#include <assert.h>
|
|
#include <cuda_fp16.h>
|
|
#include <cuda_runtime.h>
|
|
|
|
namespace tensorrt_llm::kernels::dsv3MinLatencyKernels
|
|
{
|
|
|
|
template <typename T, int kNumTokens, int kNumExperts, int kHiddenDim>
|
|
void invokeRouterGemm(float* output, T const* mat_a, T const* mat_b, cudaStream_t stream);
|
|
|
|
} // namespace tensorrt_llm::kernels::dsv3MinLatencyKernels
|