mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
4bb65f216f
* Update TensorRT-LLM --------- Co-authored-by: meghagarwal <16129366+megha95@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) 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/kernels/decodingCommon.h"
|
|
#include <cuda_fp16.h>
|
|
#include <cuda_runtime.h>
|
|
|
|
namespace tensorrt_llm
|
|
{
|
|
namespace kernels
|
|
{
|
|
|
|
template <typename T>
|
|
void invokeBanRepeatNgram(T* logits, int const** output_ids_buf, FinishedState const* finished_buf,
|
|
int const** parent_ids_buf, int const* batch_slot, int const* sequence_lengths, int batch_size, int beam_width,
|
|
int max_seq_len, int const* no_repeat_ngram_size_buf, int vocab_size_padded, size_t max_step, cudaStream_t stream);
|
|
|
|
} // namespace kernels
|
|
} // namespace tensorrt_llm
|