Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
decoding_gemm_func.h 2.25 KB
Newer Older
Li Zhang's avatar
check-in fastertransformer (#7)  
Li Zhang committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58 
/*
 * Copyright (c) 2020-2023, 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 "src/fastertransformer/utils/cublasAlgoMap.h"
#include "src/fastertransformer/utils/cuda_bf16_wrapper.h"
#include "src/fastertransformer/utils/cuda_utils.h"
#include "src/fastertransformer/utils/gemm_test/gemm_func.h"

#include <cstdio>
#include <cstdlib>
#include <ctime>
#include <cuda_fp16.h>
#include <cuda_profiler_api.h>
#include <map>
#include <sys/time.h>
#include <unistd.h>
#include <vector>

namespace fastertransformer {

template<typename T>
void generate_decoding_gemm_config(int   batch_size,
                                   int   beam_width,
                                   int   seq_len,
                                   int   head_num,
                                   int   size_per_head,
                                   int   inter_size,
                                   int   vocab_size,
                                   int   mem_hidden_units,
                                   void* buffer_in,
                                   bool  isAppend);

size_t calDecodingGemmTestBufSizeInByte(int            batch_size,
                                        int            beam_width,
                                        int            max_mem_seq_len,
                                        int            head_num,
                                        int            size_per_head,
                                        int            inter_size,
                                        int            memory_hidden_units,
                                        int            vocab_size,
                                        CublasDataType data_type);

}  // namespace fastertransformer