TensorRT-LLMs/cpp/tensorrt_llm/kernels/customMoeRoutingKernels.h
Yihan Wang 9df4dad3b6
[None][fix] Introduce inline namespace to avoid symbol collision (#9541)
Signed-off-by: Yihan Wang <yihwang@nvidia.com>
2025-12-12 23:32:15 +08:00

35 lines
1.1 KiB
C++

/*
* Copyright (c) 2025, 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/config.h"
#include <cuda_bf16.h>
#include <cuda_fp16.h>
#include "tensorrt_llm/common/cudaUtils.h"
TRTLLM_NAMESPACE_BEGIN
namespace kernels
{
template <typename InputT, typename OutputT, typename IdxT, bool DoSoftmaxBeforeTopK>
void invokeCustomMoeRouting(InputT* routerLogits, OutputT* topkValues, IdxT* topkIndices, int64_t const numTokens,
int64_t const numExperts, int64_t const topK, cudaStream_t const stream);
} // namespace kernels
TRTLLM_NAMESPACE_END