File size: 8,846 Bytes
c3b58fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
import torch
import intel_extension_for_pytorch as ipex  # pylint: disable=import-error, unused-import

# pylint: disable=protected-access, missing-function-docstring, line-too-long

original_torch_bmm = torch.bmm


def torch_bmm(input, mat2, *, out=None):
    if input.dtype != mat2.dtype:
        mat2 = mat2.to(input.dtype)

    # ARC GPUs can't allocate more than 4GB to a single block, Slice it:
    batch_size_attention, input_tokens, mat2_shape = (
        input.shape[0],
        input.shape[1],
        mat2.shape[2],
    )
    block_multiply = input.element_size()
    slice_block_size = input_tokens * mat2_shape / 1024 / 1024 * block_multiply
    block_size = batch_size_attention * slice_block_size

    split_slice_size = batch_size_attention
    if block_size > 4:
        do_split = True
        # Find something divisible with the input_tokens
        while (split_slice_size * slice_block_size) > 4:
            split_slice_size = split_slice_size // 2
            if split_slice_size <= 1:
                split_slice_size = 1
                break
    else:
        do_split = False

    split_2_slice_size = input_tokens
    if split_slice_size * slice_block_size > 4:
        slice_block_size2 = split_slice_size * mat2_shape / 1024 / 1024 * block_multiply
        do_split_2 = True
        # Find something divisible with the input_tokens
        while (split_2_slice_size * slice_block_size2) > 4:
            split_2_slice_size = split_2_slice_size // 2
            if split_2_slice_size <= 1:
                split_2_slice_size = 1
                break
    else:
        do_split_2 = False

    if do_split:
        hidden_states = torch.zeros(
            input.shape[0],
            input.shape[1],
            mat2.shape[2],
            device=input.device,
            dtype=input.dtype,
        )
        for i in range(batch_size_attention // split_slice_size):
            start_idx = i * split_slice_size
            end_idx = (i + 1) * split_slice_size
            if do_split_2:
                for i2 in range(
                    input_tokens // split_2_slice_size
                ):  # pylint: disable=invalid-name
                    start_idx_2 = i2 * split_2_slice_size
                    end_idx_2 = (i2 + 1) * split_2_slice_size
                    hidden_states[start_idx:end_idx, start_idx_2:end_idx_2] = (
                        original_torch_bmm(
                            input[start_idx:end_idx, start_idx_2:end_idx_2],
                            mat2[start_idx:end_idx, start_idx_2:end_idx_2],
                            out=out,
                        )
                    )
            else:
                hidden_states[start_idx:end_idx] = original_torch_bmm(
                    input[start_idx:end_idx], mat2[start_idx:end_idx], out=out
                )
    else:
        return original_torch_bmm(input, mat2, out=out)
    return hidden_states


original_scaled_dot_product_attention = torch.nn.functional.scaled_dot_product_attention


def scaled_dot_product_attention(
    query, key, value, attn_mask=None, dropout_p=0.0, is_causal=False
):
    # ARC GPUs can't allocate more than 4GB to a single block, Slice it:
    if len(query.shape) == 3:
        batch_size_attention, query_tokens, shape_four = query.shape
        shape_one = 1
        no_shape_one = True
    else:
        shape_one, batch_size_attention, query_tokens, shape_four = query.shape
        no_shape_one = False

    block_multiply = query.element_size()
    slice_block_size = (
        shape_one * query_tokens * shape_four / 1024 / 1024 * block_multiply
    )
    block_size = batch_size_attention * slice_block_size

    split_slice_size = batch_size_attention
    if block_size > 4:
        do_split = True
        # Find something divisible with the shape_one
        while (split_slice_size * slice_block_size) > 4:
            split_slice_size = split_slice_size // 2
            if split_slice_size <= 1:
                split_slice_size = 1
                break
    else:
        do_split = False

    split_2_slice_size = query_tokens
    if split_slice_size * slice_block_size > 4:
        slice_block_size2 = (
            shape_one * split_slice_size * shape_four / 1024 / 1024 * block_multiply
        )
        do_split_2 = True
        # Find something divisible with the batch_size_attention
        while (split_2_slice_size * slice_block_size2) > 4:
            split_2_slice_size = split_2_slice_size // 2
            if split_2_slice_size <= 1:
                split_2_slice_size = 1
                break
    else:
        do_split_2 = False

    if do_split:
        hidden_states = torch.zeros(query.shape, device=query.device, dtype=query.dtype)
        for i in range(batch_size_attention // split_slice_size):
            start_idx = i * split_slice_size
            end_idx = (i + 1) * split_slice_size
            if do_split_2:
                for i2 in range(
                    query_tokens // split_2_slice_size
                ):  # pylint: disable=invalid-name
                    start_idx_2 = i2 * split_2_slice_size
                    end_idx_2 = (i2 + 1) * split_2_slice_size
                    if no_shape_one:
                        hidden_states[start_idx:end_idx, start_idx_2:end_idx_2] = (
                            original_scaled_dot_product_attention(
                                query[start_idx:end_idx, start_idx_2:end_idx_2],
                                key[start_idx:end_idx, start_idx_2:end_idx_2],
                                value[start_idx:end_idx, start_idx_2:end_idx_2],
                                attn_mask=(
                                    attn_mask[start_idx:end_idx, start_idx_2:end_idx_2]
                                    if attn_mask is not None
                                    else attn_mask
                                ),
                                dropout_p=dropout_p,
                                is_causal=is_causal,
                            )
                        )
                    else:
                        hidden_states[:, start_idx:end_idx, start_idx_2:end_idx_2] = (
                            original_scaled_dot_product_attention(
                                query[:, start_idx:end_idx, start_idx_2:end_idx_2],
                                key[:, start_idx:end_idx, start_idx_2:end_idx_2],
                                value[:, start_idx:end_idx, start_idx_2:end_idx_2],
                                attn_mask=(
                                    attn_mask[
                                        :, start_idx:end_idx, start_idx_2:end_idx_2
                                    ]
                                    if attn_mask is not None
                                    else attn_mask
                                ),
                                dropout_p=dropout_p,
                                is_causal=is_causal,
                            )
                        )
            else:
                if no_shape_one:
                    hidden_states[start_idx:end_idx] = (
                        original_scaled_dot_product_attention(
                            query[start_idx:end_idx],
                            key[start_idx:end_idx],
                            value[start_idx:end_idx],
                            attn_mask=(
                                attn_mask[start_idx:end_idx]
                                if attn_mask is not None
                                else attn_mask
                            ),
                            dropout_p=dropout_p,
                            is_causal=is_causal,
                        )
                    )
                else:
                    hidden_states[:, start_idx:end_idx] = (
                        original_scaled_dot_product_attention(
                            query[:, start_idx:end_idx],
                            key[:, start_idx:end_idx],
                            value[:, start_idx:end_idx],
                            attn_mask=(
                                attn_mask[:, start_idx:end_idx]
                                if attn_mask is not None
                                else attn_mask
                            ),
                            dropout_p=dropout_p,
                            is_causal=is_causal,
                        )
                    )
    else:
        return original_scaled_dot_product_attention(
            query,
            key,
            value,
            attn_mask=attn_mask,
            dropout_p=dropout_p,
            is_causal=is_causal,
        )
    return hidden_states


def attention_init():
    # ARC GPUs can't allocate more than 4GB to a single block:
    torch.bmm = torch_bmm
    torch.nn.functional.scaled_dot_product_attention = scaled_dot_product_attention