mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
30 lines
1.0 KiB
C++
30 lines
1.0 KiB
C++
/*
|
|
* Copyright (c) 2020-2024, 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.
|
|
*/
|
|
|
|
#include "tensorrt_llm/runtime/iBuffer.h"
|
|
|
|
using namespace tensorrt_llm::runtime;
|
|
|
|
namespace tensorrt_llm
|
|
{
|
|
namespace kernels
|
|
{
|
|
void kvCacheBlockPartialCopy(IBuffer& dst, IBuffer const& src, unsigned int numLayers, unsigned int numHeads,
|
|
unsigned int tokensPerBlock, unsigned int numHidden, unsigned int numTokensToCopy, int kvFactor,
|
|
cudaStream_t stream);
|
|
} // namespace kernels
|
|
} // namespace tensorrt_llm
|