mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
c89653021e
* Update TensorRT-LLM --------- Co-authored-by: Eddie-Wang1120 <81598289+Eddie-Wang1120@users.noreply.github.com> Co-authored-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
35 lines
1.2 KiB
C++
35 lines
1.2 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 "cutlass/gemm_coord.h"
|
|
#include <NvInferRuntime.h>
|
|
|
|
namespace tensorrt_llm
|
|
{
|
|
namespace kernels
|
|
{
|
|
|
|
int64_t getGroupedGemmParamsWorkSpaceSize(int64_t problem_count);
|
|
|
|
void groupedGemm(std::vector<cutlass::gemm::GemmCoord> problem_sizes, std::vector<void*> ptrA, std::vector<void*> ptrB,
|
|
std::vector<void*> ptrC, std::vector<void*> ptrD, void* gemmParamsWorkspace, int64_t gemmParamsWorkSpaceSize,
|
|
void* gemmWorkSpace, int64_t gemmWorkspaceSize, bool isLoraIn, nvinfer1::DataType dataType, cudaStream_t stream);
|
|
|
|
} // namespace kernels
|
|
|
|
} // namespace tensorrt_llm
|