File size: 5,185 Bytes
e45d058
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
/* coding=utf-8

 * Copyright (c) 2021, 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 <cuda_fp16.h>
#include <torch/extension.h>
#include <vector>

namespace multihead_attn {
namespace fused_softmax {
namespace scaled_masked_softmax {

torch::Tensor fwd_cuda(

    torch::Tensor const& input, 

    torch::Tensor const& mask,

    float scale_factor);

torch::Tensor bwd_cuda(

    torch::Tensor const& output_grads, 

    torch::Tensor const& softmax_results,

    float scale_factor);

int get_batch_per_block_cuda(

    int query_seq_len,

    int key_seq_len,

    int batches,

    int attn_heads);

torch::Tensor fwd(

    torch::Tensor const& input,

    torch::Tensor const& mask,

    float scale_factor) {
  AT_ASSERTM(input.dim() == 4, "expected 4D tensor");
  AT_ASSERTM((input.scalar_type() == at::ScalarType::Half) ||
	     (input.scalar_type() == at::ScalarType::BFloat16), 
      "Only fp16 and bf16 are supported");
  AT_ASSERTM(mask.dim() == 4, "expected 4D tensor");

  return fwd_cuda(input, mask, scale_factor);
}

torch::Tensor bwd(

    torch::Tensor const& output_grads, 

    torch::Tensor const& softmax_results,

    float scale_factor) {

  AT_ASSERTM(output_grads.dim() == 4, "expected 3D tensor");
  AT_ASSERTM(softmax_results.dim() == 4, "expected 3D tensor");

  AT_ASSERTM((output_grads.scalar_type() == at::ScalarType::Half) ||
	     (output_grads.scalar_type() == at::ScalarType::BFloat16), 
      "Only fp16 and bf16 are supported");
  AT_ASSERTM((softmax_results.scalar_type() == at::ScalarType::Half) ||
	     (softmax_results.scalar_type() == at::ScalarType::BFloat16), 
      "Only fp16 and bf16 are supported");

  return bwd_cuda(output_grads, softmax_results, scale_factor);
}

int get_batch_per_block(

    int query_seq_len,

    int key_seq_len,

    int batches,

    int attn_heads) {
    return get_batch_per_block_cuda(query_seq_len, key_seq_len, batches, attn_heads);
}

} // end namespace scaled_masked_softmax
} // end namespace fused_softmax
} // end namespace multihead_attn

namespace multihead_attn {
namespace fused_softmax {
namespace scaled_upper_triang_masked_softmax {

torch::Tensor fwd_cuda(

    torch::Tensor const& input,

    float scale_factor);

torch::Tensor bwd_cuda(

    torch::Tensor const& output_grads,

    torch::Tensor const& softmax_results,

    float scale_factor);

torch::Tensor fwd(torch::Tensor const& input, float scale_factor) {
  AT_ASSERTM(input.dim() == 3, "expected 3D tensor");
  AT_ASSERTM((input.scalar_type() == at::ScalarType::Half) ||
	     (input.scalar_type() == at::ScalarType::BFloat16),
      "Only fp16 and bf16 are supported");

  return fwd_cuda(input, scale_factor);
}

torch::Tensor bwd(

    torch::Tensor const& output_grads,

    torch::Tensor const& softmax_results,

    float scale_factor) {

  AT_ASSERTM(output_grads.dim() == 3, "expected 3D tensor");
  AT_ASSERTM(softmax_results.dim() == 3, "expected 3D tensor");

  AT_ASSERTM((output_grads.scalar_type() == at::ScalarType::Half) ||
	     (output_grads.scalar_type() == at::ScalarType::BFloat16),
      "Only fp16 and bf16 are supported");
  AT_ASSERTM((softmax_results.scalar_type() == at::ScalarType::Half) ||
	     (softmax_results.scalar_type() == at::ScalarType::BFloat16),
      "Only fp16 and bf16 are supported");

  return bwd_cuda(output_grads, softmax_results, scale_factor);
}

} // end namespace scaled_upper_triang_masked_softmax
} // end namespace fused_softmax
} // end namespace multihead_attn

PYBIND11_MODULE(TORCH_EXTENSION_NAME, m) {
  m.def("scaled_masked_softmax_forward",
        &multihead_attn::fused_softmax::scaled_masked_softmax::fwd, 
	"Self Multihead Attention scaled, time masked softmax -- Forward.");

  m.def("scaled_masked_softmax_backward",
        &multihead_attn::fused_softmax::scaled_masked_softmax::bwd,
	"Self Multihead Attention scaled, time masked softmax -- Backward.");

  m.def("scaled_masked_softmax_get_batch_per_block",
        &multihead_attn::fused_softmax::scaled_masked_softmax::get_batch_per_block,
        "Return Batch per block size."
  );

  m.def("scaled_upper_triang_masked_softmax_forward",
        &multihead_attn::fused_softmax::scaled_upper_triang_masked_softmax::fwd,
        "Self Multihead Attention scaled, time masked softmax -- Forward.");
  m.def("scaled_upper_triang_masked_softmax_backward",
        &multihead_attn::fused_softmax::scaled_upper_triang_masked_softmax::bwd,
        "Self Multihead Attention scaled, time masked softmax -- Backward.");
}