File size: 2,037 Bytes
c295391
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# MIT License

# Copyright (c) Microsoft

# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:

# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.

# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

# Copyright (c) [2025] [Microsoft]
# SPDX-License-Identifier: MIT
import torch
import torch.nn as nn
from . import SparseTensor

__all__ = [
    'SparseReLU',
    'SparseSiLU',
    'SparseGELU',
    'SparseActivation'
]


class SparseReLU(nn.ReLU):
    def forward(self, input: SparseTensor) -> SparseTensor:
        return input.replace(super().forward(input.feats))
    

class SparseSiLU(nn.SiLU):
    def forward(self, input: SparseTensor) -> SparseTensor:
        return input.replace(super().forward(input.feats))


class SparseGELU(nn.GELU):
    def forward(self, input: SparseTensor) -> SparseTensor:
        return input.replace(super().forward(input.feats))


class SparseActivation(nn.Module):
    def __init__(self, activation: nn.Module):
        super().__init__()
        self.activation = activation

    def forward(self, input: SparseTensor) -> SparseTensor:
        return input.replace(self.activation(input.feats))