mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
40 lines
1.2 KiB
C++
40 lines
1.2 KiB
C++
/*
|
|
* Copyright (c) 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.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include "tensorrt_llm/common/config.h"
|
|
#include "tensorrt_llm/runtime/common.h"
|
|
#include <cuda_fp16.h>
|
|
#include <cuda_runtime.h>
|
|
|
|
TRTLLM_NAMESPACE_BEGIN
|
|
|
|
namespace kernels
|
|
{
|
|
|
|
template <typename T>
|
|
void invokeLogitsBitmask(
|
|
T** logits, uint32_t const** bitmask, int32_t batchSize, int32_t vocabSizePadded, cudaStream_t stream);
|
|
|
|
template <typename T>
|
|
void invokeContiguousLogitsBitmask(T* logits, uint32_t const* bitmask, int32_t const* tokenMask, int32_t const* d2t,
|
|
int32_t batchSize, int32_t vocabSizePadded, int32_t bitmaskSize, cudaStream_t stream);
|
|
|
|
} // namespace kernels
|
|
|
|
TRTLLM_NAMESPACE_END
|