Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
fattn.cu 13.9 KB
Newer Older
xuxzh1's avatar
init  
xuxzh1 committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15 
#include "common.cuh"
#include "fattn-common.cuh"
#include "fattn-tile-f16.cuh"
#include "fattn-tile-f32.cuh"
#include "fattn-vec-f16.cuh"
#include "fattn-vec-f32.cuh"
#include "fattn-wmma-f16.cuh"
#include "fattn.cuh"

#include <cstdint>

static void ggml_cuda_flash_attn_ext_wmma_f16(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
    const ggml_tensor * KQV = dst;
    const ggml_tensor * Q   = dst->src[0];
xuxzh1's avatar
update  
xuxzh1 committed
16 
    const enum ggml_prec prec = ggml_flash_attn_ext_get_prec(KQV);
xuxzh1's avatar
init  
xuxzh1 committed
17
xuxzh1's avatar
update  
xuxzh1 committed
18 
    if (prec != GGML_PREC_DEFAULT) {
xuxzh1's avatar
init  
xuxzh1 committed
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 
        if (Q->ne[1] <= 32 || Q->ne[0] > 128) {
            constexpr int cols_per_block = 16;
            switch (Q->ne[0]) {
                case 64:
                    ggml_cuda_flash_attn_ext_wmma_f16_case< 64, cols_per_block, float>(ctx, dst);
                    break;
                case 80:
                    ggml_cuda_flash_attn_ext_wmma_f16_case< 80, cols_per_block, float>(ctx, dst);
                    break;
                case 96:
                    ggml_cuda_flash_attn_ext_wmma_f16_case< 96, cols_per_block, float>(ctx, dst);
                    break;
                case 112:
                    ggml_cuda_flash_attn_ext_wmma_f16_case<112, cols_per_block, float>(ctx, dst);
                    break;
                case 128:
                    ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, float>(ctx, dst);
                    break;
                case 256:
                    ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, float>(ctx, dst);
                    break;
                default:
                    GGML_ABORT("fatal error");
                    break;
            }
        } else {
            constexpr int cols_per_block = 32;
            switch (Q->ne[0]) {
                case 64:
                    ggml_cuda_flash_attn_ext_wmma_f16_case< 64, cols_per_block, float>(ctx, dst);
                    break;
                case 80:
                    ggml_cuda_flash_attn_ext_wmma_f16_case< 80, cols_per_block, float>(ctx, dst);
                    break;
                case 96:
                    ggml_cuda_flash_attn_ext_wmma_f16_case< 96, cols_per_block, float>(ctx, dst);
                    break;
                case 112:
                    ggml_cuda_flash_attn_ext_wmma_f16_case<112, cols_per_block, float>(ctx, dst);
                    break;
                case 128:
                    ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, float>(ctx, dst);
                    break;
                // case 256:
                //     ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, float>(ctx, dst);
                //     break;
                default:
                    GGML_ABORT("fatal error");
                    break;
            }
        }
        return;
    }

    if (Q->ne[1] <= 8 && Q->ne[0] % WARP_SIZE == 0) {
        constexpr int cols_per_block = 8;
        switch (Q->ne[0]) {
            case 64:
                ggml_cuda_flash_attn_ext_wmma_f16_case< 64, cols_per_block, half>(ctx, dst);
                break;
            case 96:
                ggml_cuda_flash_attn_ext_wmma_f16_case< 96, cols_per_block, half>(ctx, dst);
                break;
            case 128:
                ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, half>(ctx, dst);
                break;
            case 256:
                ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, half>(ctx, dst);
                break;
            default:
                GGML_ABORT("fatal error");
                break;
        }
        return;
    }

    if (Q->ne[1] <= 32) {
        constexpr int cols_per_block = 16;
        switch (Q->ne[0]) {
            case 64:
                ggml_cuda_flash_attn_ext_wmma_f16_case< 64, cols_per_block, half>(ctx, dst);
                break;
            case 80:
                ggml_cuda_flash_attn_ext_wmma_f16_case< 80, cols_per_block, half>(ctx, dst);
                break;
            case 96:
                ggml_cuda_flash_attn_ext_wmma_f16_case< 96, cols_per_block, half>(ctx, dst);
                break;
            case 112:
                ggml_cuda_flash_attn_ext_wmma_f16_case<112, cols_per_block, half>(ctx, dst);
                break;
            case 128:
                ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, half>(ctx, dst);
                break;
            case 256:
                ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, half>(ctx, dst);
                break;
            default:
                GGML_ABORT("fatal error");
                break;
        }
        return;
    }

    constexpr int cols_per_block = 32;
    switch (Q->ne[0]) {
        case 64:
            ggml_cuda_flash_attn_ext_wmma_f16_case< 64, cols_per_block, half>(ctx, dst);
            break;
        case 80:
            ggml_cuda_flash_attn_ext_wmma_f16_case< 80, cols_per_block, half>(ctx, dst);
            break;
        case 96:
            ggml_cuda_flash_attn_ext_wmma_f16_case< 96, cols_per_block, half>(ctx, dst);
            break;
        case 112:
            ggml_cuda_flash_attn_ext_wmma_f16_case<112, cols_per_block, half>(ctx, dst);
            break;
        case 128:
            ggml_cuda_flash_attn_ext_wmma_f16_case<128, cols_per_block, half>(ctx, dst);
            break;
        case 256:
            ggml_cuda_flash_attn_ext_wmma_f16_case<256, cols_per_block, half>(ctx, dst);
            break;
        default:
            GGML_ABORT("fatal error");
            break;
    }
}
#define FATTN_VEC_F16_CASE(D, type_K, type_V)                               \
    if (Q->ne[0] == (D) && K->type == (type_K) && V->type == (type_V)) {    \
        ggml_cuda_flash_attn_ext_vec_f16_case<D, type_K, type_V>(ctx, dst); \
        return;                                                             \
    }                                                                       \

static void ggml_cuda_flash_attn_ext_vec_f16(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
xuxzh1's avatar
update  
xuxzh1 committed
155 
    ggml_tensor * Q = dst->src[0];
xuxzh1's avatar
init  
xuxzh1 committed
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
220
221
222
223
224
225
226
227
228
229 
    ggml_tensor * K = dst->src[1];
    ggml_tensor * V = dst->src[2];

#ifdef GGML_CUDA_FA_ALL_QUANTS
    FATTN_VEC_F16_CASE( 64, GGML_TYPE_F16, GGML_TYPE_Q4_0)
    FATTN_VEC_F16_CASE( 64, GGML_TYPE_F16, GGML_TYPE_Q4_1)
    FATTN_VEC_F16_CASE( 64, GGML_TYPE_F16, GGML_TYPE_Q5_0)
    FATTN_VEC_F16_CASE( 64, GGML_TYPE_F16, GGML_TYPE_Q5_1)
    FATTN_VEC_F16_CASE( 64, GGML_TYPE_F16, GGML_TYPE_Q8_0)
    FATTN_VEC_F16_CASE( 64, GGML_TYPE_F16, GGML_TYPE_F16 )

    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_F16,  GGML_TYPE_Q4_0)

    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_1)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_1)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_1)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_1)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_1)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_F16,  GGML_TYPE_Q4_1)

    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_F16,  GGML_TYPE_Q5_0)

    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_1)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_1)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_1)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_1)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_1)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_F16,  GGML_TYPE_Q5_1)

    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q8_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q8_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q8_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q8_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_F16,  GGML_TYPE_Q8_0)

    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_F16)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_F16)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_F16)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_F16)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_F16)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_F16,  GGML_TYPE_F16)

    FATTN_VEC_F16_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16)
#else
    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0)

    FATTN_VEC_F16_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0)

    FATTN_VEC_F16_CASE( 64, GGML_TYPE_F16, GGML_TYPE_F16)
    FATTN_VEC_F16_CASE(128, GGML_TYPE_F16, GGML_TYPE_F16)
    FATTN_VEC_F16_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16)
#endif // GGML_CUDA_FA_ALL_QUANTS

    on_no_fattn_vec_case(Q->ne[0]);
}

#define FATTN_VEC_F32_CASE(D, type_K, type_V)                               \
    if (Q->ne[0] == (D) && K->type == (type_K) && V->type == (type_V)) {    \
        ggml_cuda_flash_attn_ext_vec_f32_case<D, type_K, type_V>(ctx, dst); \
        return;                                                             \
    }                                                                       \

static void ggml_cuda_flash_attn_ext_vec_f32(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
xuxzh1's avatar
update  
xuxzh1 committed
230 
    ggml_tensor * Q = dst->src[0];
xuxzh1's avatar
init  
xuxzh1 committed
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303 
    ggml_tensor * K = dst->src[1];
    ggml_tensor * V = dst->src[2];

#ifdef GGML_CUDA_FA_ALL_QUANTS
    FATTN_VEC_F32_CASE( 64, GGML_TYPE_F16, GGML_TYPE_Q4_0)
    FATTN_VEC_F32_CASE( 64, GGML_TYPE_F16, GGML_TYPE_Q4_1)
    FATTN_VEC_F32_CASE( 64, GGML_TYPE_F16, GGML_TYPE_Q5_0)
    FATTN_VEC_F32_CASE( 64, GGML_TYPE_F16, GGML_TYPE_Q5_1)
    FATTN_VEC_F32_CASE( 64, GGML_TYPE_F16, GGML_TYPE_Q8_0)
    FATTN_VEC_F32_CASE( 64, GGML_TYPE_F16, GGML_TYPE_F16)

    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_F16,  GGML_TYPE_Q4_0)

    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_1)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q4_1)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q4_1)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q4_1)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q4_1)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_F16,  GGML_TYPE_Q4_1)

    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_F16,  GGML_TYPE_Q5_0)

    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q5_1)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q5_1)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q5_1)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q5_1)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q5_1)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_F16,  GGML_TYPE_Q5_1)

    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q8_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_Q8_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_Q8_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_Q8_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_F16,  GGML_TYPE_Q8_0)

    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_F16)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_1, GGML_TYPE_F16)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_0, GGML_TYPE_F16)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q5_1, GGML_TYPE_F16)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_F16)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_F16,  GGML_TYPE_F16)

    FATTN_VEC_F32_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16)
#else
    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q4_0, GGML_TYPE_Q4_0)

    FATTN_VEC_F32_CASE(128, GGML_TYPE_Q8_0, GGML_TYPE_Q8_0)

    FATTN_VEC_F32_CASE( 64, GGML_TYPE_F16, GGML_TYPE_F16)
    FATTN_VEC_F32_CASE(128, GGML_TYPE_F16, GGML_TYPE_F16)
    FATTN_VEC_F32_CASE(256, GGML_TYPE_F16, GGML_TYPE_F16)
#endif // GGML_CUDA_FA_ALL_QUANTS

    on_no_fattn_vec_case(Q->ne[0]);
}

void ggml_cuda_flash_attn_ext(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
    const ggml_tensor * KQV = dst;
    const ggml_tensor * Q   = dst->src[0];

    ggml_cuda_set_device(ctx.device);
    const int cc = ggml_cuda_info().devices[ggml_cuda_get_device()].cc;
xuxzh1's avatar
update  
xuxzh1 committed
304 
    const enum ggml_prec prec = ggml_flash_attn_ext_get_prec(KQV);
xuxzh1's avatar
init  
xuxzh1 committed
305
306
307 

    // On AMD the tile kernels perform poorly, use the vec kernel instead:
    if (cc >= CC_OFFSET_AMD) {
xuxzh1's avatar
update  
xuxzh1 committed
308 
        if (prec == GGML_PREC_DEFAULT && fast_fp16_available(cc)) {
xuxzh1's avatar
init  
xuxzh1 committed
309
310
311
312
313
314
315
316 
            ggml_cuda_flash_attn_ext_vec_f16(ctx, dst);
        } else {
            ggml_cuda_flash_attn_ext_vec_f32(ctx, dst);
        }
        return;
    }

    if (!fast_fp16_available(cc)) {
xuxzh1's avatar
update  
xuxzh1 committed
317 
        if (Q->ne[1] <= 8 || Q->ne[0] == 256) {
xuxzh1's avatar
init  
xuxzh1 committed
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334 
            ggml_cuda_flash_attn_ext_vec_f32(ctx, dst);
        } else {
            ggml_cuda_flash_attn_ext_tile_f32(ctx, dst);
        }
        return;
    }

    if (!fp16_mma_available(cc)) {
        if (Q->ne[1] <= 8) {
            ggml_cuda_flash_attn_ext_vec_f16(ctx, dst);
        } else {
            ggml_cuda_flash_attn_ext_tile_f16(ctx, dst);
        }
        return;
    }

    if (Q->ne[1] == 1 && Q->ne[0] % (2*WARP_SIZE) == 0) {
xuxzh1's avatar
update  
xuxzh1 committed
335 
        if (prec == GGML_PREC_DEFAULT) {
xuxzh1's avatar
init  
xuxzh1 committed
336
337
338
339
340
341
342
343
344
345 
            ggml_cuda_flash_attn_ext_vec_f16(ctx, dst);
            return;
        } else if(Q->ne[0] <= 128) {
            ggml_cuda_flash_attn_ext_vec_f32(ctx, dst);
            return;
        }
    }

    ggml_cuda_flash_attn_ext_wmma_f16(ctx, dst);
}