File size: 44,799 Bytes
f8c5b0d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
220
221
222
223
224
225
226
227
228
229
230
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
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
#pragma once

//
// GGML Tensor Library
//
// This documentation is still a work in progress.
// If you wish some specific topics to be covered, feel free to drop a comment:
//
//   https://github.com/ggerganov/whisper.cpp/issues/40
//
// ## Overview
//
// This library implements:
//
//  - a set of tensor operations
//  - automatic differentiation
//  - basic optimization algorithms
//
// The aim of this library is to provide a minimalistic approach for various machine learning tasks. This includes,
// but is not limited to, the following:
//
//  - linear regression
//  - support vector machines
//  - neural networks
//
// The library allows the user to define a certain function using the available tensor operations. This function
// definition is represented internally via a computation graph. Each tensor operation in the function definition
// corresponds to a node in the graph. Having the computation graph defined, the user can choose to compute the
// function's value and/or its gradient with respect to the input variables. Optionally, the function can be optimized
// using one of the available optimization algorithms.
//
// For example, here we define the function: f(x) = a*x^2 + b
//
//   {
//       struct ggml_init_params params = {
//           .mem_size   = 16*1024*1024,
//           .mem_buffer = NULL,
//       };
//
//       // memory allocation happens here
//       struct ggml_context * ctx = ggml_init(params);
//
//       struct ggml_tensor * x = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, 1);
//
//       ggml_set_param(ctx, x); // x is an input variable
//
//       struct ggml_tensor * a  = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, 1);
//       struct ggml_tensor * b  = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, 1);
//       struct ggml_tensor * x2 = ggml_mul(ctx, x, x);
//       struct ggml_tensor * f  = ggml_add(ctx, ggml_mul(ctx, a, x2), b);
//
//       ...
//   }
//
// Notice that the function definition above does not involve any actual computation. The computation is performed only
// when the user explicitly requests it. For example, to compute the function's value at x = 2.0:
//
//   {
//       ...
//
//       struct ggml_cgraph gf = ggml_build_forward(f);
//
//       // set the input variable and parameter values
//       ggml_set_f32(x, 2.0f);
//       ggml_set_f32(a, 3.0f);
//       ggml_set_f32(b, 4.0f);
//
//       ggml_graph_compute(ctx0, &gf);
//
//       printf("f = %f\n", ggml_get_f32_1d(f, 0));
//
//       ...
//   }
//
// The actual computation is performed in the ggml_graph_compute() function.
//
// The ggml_new_tensor_...() functions create new tensors. They are allocated in the memory buffer provided to the
// ggml_init() function. You have to be careful not to exceed the memory buffer size. Therefore, you have to know
// in advance how much memory you need for your computation. Alternatively, you can allocate a large enough memory
// and after defining the computation graph, call the ggml_used_mem() function to find out how much memory was
// actually needed.
//
// The ggml_set_param() function marks a tensor as an input variable. This is used by the automatic
// differentiation and optimization algorithms.
//
// The described approach allows to define the function graph once and then compute its forward or backward graphs
// multiple times. All computations will use the same memory buffer allocated in the ggml_init() function. This way
// the user can avoid the memory allocation overhead at runtime.
//
// The library supports multi-dimensional tensors - up to 4 dimensions. The FP16 and FP32 data types are first class
// citizens, but in theory the library can be extended to support FP8 and integer data types.
//
// Each tensor operation produces a new tensor. Initially the library was envisioned to support only the use of unary
// and binary operations. Most of the available operations fall into one of these two categories. With time, it became
// clear that the library needs to support more complex operations. The way to support these operations is not clear
// yet, but a few examples are demonstrated in the following operations:
//
//   - ggml_permute()
//   - ggml_conv_1d_1s()
//   - ggml_conv_1d_2s()
//
// For each tensor operator, the library implements a forward and backward computation function. The forward function
// computes the output tensor value given the input tensor values. The backward function computes the adjoint of the
// input tensors given the adjoint of the output tensor. For a detailed explanation of what this means, take a
// calculus class, or watch the following video:
//
//   What is Automatic Differentiation?
//   https://www.youtube.com/watch?v=wG_nF1awSSY
//
//
// ## Tensor data (struct ggml_tensor)
//
// The tensors are stored in memory via the ggml_tensor struct. The structure provides information about the size of
// the tensor, the data type, and the memory buffer where the tensor data is stored. Additionally, it contains
// pointers to the "source" tensors - i.e. the tensors that were used to compute the current tensor. For example:
//
//   {
//       struct ggml_tensor * c = ggml_add(ctx, a, b);
//
//       assert(c->src[0] == a);
//       assert(c->src[1] == b);
//   }
//
// The multi-dimensional tensors are stored in row-major order. The ggml_tensor struct contains fields for the
// number of elements in each dimension ("ne") as well as the number of bytes ("nb", a.k.a. stride). This allows
// to store tensors that are not contiguous in memory, which is useful for operations such as transposition and
// permutation. All tensor operations have to take the stride into account and not assume that the tensor is
// contiguous in memory.
//
// The data of the tensor is accessed via the "data" pointer. For example:
//
//   {
//       struct ggml_tensor * a = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, 2, 3);
//
//       // a[1, 2] = 1.0f;
//       *(float *) ((char *) a->data + 2*a->nb[1] + 1*a->nb[0]) = 1.0f;
//
//       // a[2, 0] = 2.0f;
//       *(float *) ((char *) a->data + 0*a->nb[1] + 2*a->nb[0]) = 2.0f;
//
//       ...
//   }
//
// Alternatively, there are helper functions, such as ggml_get_f32_1d() and ggml_set_f32_1d() that can be used.
//
// ## The matrix multiplication operator (ggml_mul_mat)
//
// TODO
//
//
// ## Multi-threading
//
// TODO
//
//
// ## Overview of ggml.c
//
// TODO
//
//
// ## SIMD optimizations
//
// TODO
//
//
// ## Debugging ggml
//
// TODO
//
//

#ifdef GGML_SHARED
#    if defined(_WIN32) && !defined(__MINGW32__)
#        ifdef GGML_BUILD
#            define GGML_API __declspec(dllexport)
#        else
#            define GGML_API __declspec(dllimport)
#        endif
#    else
#        define GGML_API __attribute__ ((visibility ("default")))
#    endif
#else
#    define GGML_API
#endif

#include <stdint.h>
#include <stddef.h>
#include <stdbool.h>

#define GGML_FILE_MAGIC   0x67676d6c // "ggml"
#define GGML_FILE_VERSION 1

#define GGML_QNT_VERSION        2    // bump this on quantization format changes
#define GGML_QNT_VERSION_FACTOR 1000 // do not change this

#define GGML_MAX_DIMS          4
#define GGML_MAX_NODES         4096
#define GGML_MAX_PARAMS        256
#define GGML_MAX_CONTEXTS      64
#define GGML_MAX_OPT           4
#define GGML_MAX_NAME          32
#define GGML_DEFAULT_N_THREADS 4

#define GGML_ASSERT(x) \
    do { \
        if (!(x)) { \
            fprintf(stderr, "GGML_ASSERT: %s:%d: %s\n", __FILE__, __LINE__, #x); \
            abort(); \
        } \
    } while (0)

#ifdef  __cplusplus
extern "C" {
#endif

#ifdef __ARM_NEON
    // we use the built-in 16-bit float type
    typedef __fp16 ggml_fp16_t;
#else
    typedef uint16_t ggml_fp16_t;
#endif

    // convert FP16 <-> FP32
    GGML_API float       ggml_fp16_to_fp32(ggml_fp16_t x);
    GGML_API ggml_fp16_t ggml_fp32_to_fp16(float x);

    GGML_API void ggml_fp16_to_fp32_row(const ggml_fp16_t * x, float * y, size_t n);
    GGML_API void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, size_t n);

    struct ggml_object;
    struct ggml_context;

    enum ggml_type {
        GGML_TYPE_F32  = 0,
        GGML_TYPE_F16  = 1,
        GGML_TYPE_Q4_0 = 2,
        GGML_TYPE_Q4_1 = 3,
        // GGML_TYPE_Q4_2 = 4, support has been removed
        // GGML_TYPE_Q4_3 (5) support has been removed
        GGML_TYPE_Q5_0 = 6,
        GGML_TYPE_Q5_1 = 7,
        GGML_TYPE_Q8_0 = 8,
        GGML_TYPE_Q8_1 = 9,
        // k-quantizations
        GGML_TYPE_Q2_K = 10,
        GGML_TYPE_Q3_K = 11,
        GGML_TYPE_Q4_K = 12,
        GGML_TYPE_Q5_K = 13,
        GGML_TYPE_Q6_K = 14,
        GGML_TYPE_Q8_K = 15,
        GGML_TYPE_I8,
        GGML_TYPE_I16,
        GGML_TYPE_I32,
        GGML_TYPE_COUNT,
    };

    enum ggml_backend {
        GGML_BACKEND_CPU = 0,
        GGML_BACKEND_GPU = 10,
        GGML_BACKEND_GPU_SPLIT = 20,
    };

    // model file types
    enum ggml_ftype {
        GGML_FTYPE_UNKNOWN     = -1,
        GGML_FTYPE_ALL_F32     = 0,
        GGML_FTYPE_MOSTLY_F16  = 1,  // except 1d tensors
        GGML_FTYPE_MOSTLY_Q4_0 = 2,  // except 1d tensors
        GGML_FTYPE_MOSTLY_Q4_1 = 3,  // except 1d tensors
        GGML_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4, // tok_embeddings.weight and output.weight are F16
        GGML_FTYPE_MOSTLY_Q8_0 = 7,  // except 1d tensors
        GGML_FTYPE_MOSTLY_Q5_0 = 8,  // except 1d tensors
        GGML_FTYPE_MOSTLY_Q5_1 = 9,  // except 1d tensors
        GGML_FTYPE_MOSTLY_Q2_K = 10, // except 1d tensors
        GGML_FTYPE_MOSTLY_Q3_K = 11, // except 1d tensors
        GGML_FTYPE_MOSTLY_Q4_K = 12, // except 1d tensors
        GGML_FTYPE_MOSTLY_Q5_K = 13, // except 1d tensors
        GGML_FTYPE_MOSTLY_Q6_K = 14, // except 1d tensors
    };

    // available tensor operations:
    enum ggml_op {
        GGML_OP_NONE = 0,

        GGML_OP_DUP,
        GGML_OP_ADD,
        GGML_OP_ADD1,
        GGML_OP_ACC,
        GGML_OP_SUB,
        GGML_OP_MUL,
        GGML_OP_DIV,
        GGML_OP_SQR,
        GGML_OP_SQRT,
        GGML_OP_LOG,
        GGML_OP_SUM,
        GGML_OP_SUM_ROWS,
        GGML_OP_MEAN,
        GGML_OP_REPEAT,
        GGML_OP_REPEAT_BACK,
        GGML_OP_ABS,
        GGML_OP_SGN,
        GGML_OP_NEG,
        GGML_OP_STEP,
        GGML_OP_RELU,
        GGML_OP_GELU,
        GGML_OP_SILU,
        GGML_OP_SILU_BACK,
        GGML_OP_NORM, // normalize
        GGML_OP_RMS_NORM,
        GGML_OP_RMS_NORM_BACK,

        GGML_OP_MUL_MAT,
        GGML_OP_OUT_PROD,

        GGML_OP_SCALE,
        GGML_OP_SET,
        GGML_OP_CPY,
        GGML_OP_CONT,
        GGML_OP_RESHAPE,
        GGML_OP_VIEW,
        GGML_OP_PERMUTE,
        GGML_OP_TRANSPOSE,
        GGML_OP_GET_ROWS,
        GGML_OP_GET_ROWS_BACK,
        GGML_OP_DIAG,
        GGML_OP_DIAG_MASK_INF,
        GGML_OP_DIAG_MASK_ZERO,
        GGML_OP_SOFT_MAX,
        GGML_OP_SOFT_MAX_BACK,
        GGML_OP_ROPE,
        GGML_OP_ROPE_BACK,
        GGML_OP_ALIBI,
        GGML_OP_CLAMP,
        GGML_OP_CONV_1D_1S,
        GGML_OP_CONV_1D_2S,

        GGML_OP_FLASH_ATTN,
        GGML_OP_FLASH_FF,
        GGML_OP_FLASH_ATTN_BACK,

        GGML_OP_MAP_UNARY,
        GGML_OP_MAP_BINARY,

        GGML_OP_CROSS_ENTROPY_LOSS,
        GGML_OP_CROSS_ENTROPY_LOSS_BACK,

        GGML_OP_COUNT,
    };


    // ggml object
    struct ggml_object {
        size_t offs;
        size_t size;

        struct ggml_object * next;

        char padding[8];
    };

    static const size_t GGML_OBJECT_SIZE = sizeof(struct ggml_object);

    // n-dimensional tensor
    struct ggml_tensor {
        enum ggml_type    type;
        enum ggml_backend backend;

        int     n_dims;
        int64_t ne[GGML_MAX_DIMS]; // number of elements
        size_t  nb[GGML_MAX_DIMS]; // stride in bytes:
                                   // nb[0] = sizeof(type)
                                   // nb[1] = nb[0]   * ne[0] + padding
                                   // nb[i] = nb[i-1] * ne[i-1]

        // compute data
        enum ggml_op op;

        bool is_param;

        struct ggml_tensor * grad;
        struct ggml_tensor * src0;
        struct ggml_tensor * src1;
        struct ggml_tensor * opt[GGML_MAX_OPT];

        // thread scheduling
        int n_tasks;

        // performance
        int     perf_runs;
        int64_t perf_cycles;
        int64_t perf_time_us;

        void * data;

        char name[GGML_MAX_NAME];

        void * extra; // extra things e.g. for ggml-cuda.cu

        char padding[4];
    };

    static const size_t GGML_TENSOR_SIZE = sizeof(struct ggml_tensor);

    // computation graph
    struct ggml_cgraph {
        int n_nodes;
        int n_leafs;
        int n_threads;

        size_t work_size;
        struct ggml_tensor * work;

        struct ggml_tensor * nodes[GGML_MAX_NODES];
        struct ggml_tensor * grads[GGML_MAX_NODES];
        struct ggml_tensor * leafs[GGML_MAX_NODES];

        // performance
        int     perf_runs;
        int64_t perf_cycles;
        int64_t perf_time_us;
    };

    // scratch buffer
    struct ggml_scratch {
        size_t offs;
        size_t size;
        void * data;
    };

    struct ggml_init_params {
        // memory pool
        size_t mem_size;   // bytes
        void * mem_buffer; // if NULL, memory will be allocated internally
        bool   no_alloc;   // don't allocate memory for the tensor data
    };


    // compute types
    enum ggml_task_type {
        GGML_TASK_INIT = 0,
        GGML_TASK_COMPUTE,
        GGML_TASK_FINALIZE,
    };

    struct ggml_compute_params {
        enum ggml_task_type type;

        // ith = thread index, nth = number of threads
        int ith, nth;

        // work buffer for all threads
        size_t wsize;
        void * wdata;
    };

    // misc

    GGML_API void    ggml_time_init(void); // call this once at the beginning of the program
    GGML_API int64_t ggml_time_ms(void);
    GGML_API int64_t ggml_time_us(void);
    GGML_API int64_t ggml_cycles(void);
    GGML_API int64_t ggml_cycles_per_ms(void);

    GGML_API void    ggml_print_object (const struct ggml_object * obj);
    GGML_API void    ggml_print_objects(const struct ggml_context * ctx);

    GGML_API int64_t ggml_nelements   (const struct ggml_tensor * tensor);
    GGML_API int64_t ggml_nrows       (const struct ggml_tensor * tensor);
    GGML_API size_t  ggml_nbytes      (const struct ggml_tensor * tensor);
    GGML_API size_t  ggml_nbytes_split(const struct ggml_tensor * tensor, int nrows_split);

    GGML_API int     ggml_blck_size (enum ggml_type type);
    GGML_API size_t  ggml_type_size (enum ggml_type type); // size in bytes for all elements in a block
    GGML_API float   ggml_type_sizef(enum ggml_type type); // ggml_type_size()/ggml_blck_size() as float

    GGML_API const char * ggml_type_name(enum ggml_type type);
    GGML_API const char * ggml_op_name  (enum ggml_op   op);

    GGML_API size_t  ggml_element_size(const struct ggml_tensor * tensor);

    GGML_API bool    ggml_is_quantized(enum ggml_type type);

    // TODO: temporary until model loading of ggml examples is refactored
    GGML_API enum ggml_type ggml_ftype_to_ggml_type(enum ggml_ftype ftype);

    GGML_API bool ggml_is_transposed(const struct ggml_tensor * tensor);
    GGML_API bool ggml_is_contiguous(const struct ggml_tensor * tensor);
    GGML_API bool ggml_is_permuted  (const struct ggml_tensor * tensor);

    // use this to compute the memory overhead of a tensor
    GGML_API size_t ggml_tensor_overhead(void);

    // main

    GGML_API struct ggml_context * ggml_init(struct ggml_init_params params);
    GGML_API void                  ggml_free(struct ggml_context * ctx);

    GGML_API size_t  ggml_used_mem(const struct ggml_context * ctx);

    GGML_API size_t  ggml_set_scratch (struct ggml_context * ctx, struct ggml_scratch scratch);
    GGML_API void    ggml_set_no_alloc(struct ggml_context * ctx, bool no_alloc);

    GGML_API void *  ggml_get_mem_buffer(struct ggml_context * ctx);
    GGML_API size_t  ggml_get_mem_size  (struct ggml_context * ctx);

    GGML_API struct ggml_tensor * ggml_new_tensor(
            struct ggml_context * ctx,
            enum   ggml_type type,
            int    n_dims,
            const int64_t *ne);

    GGML_API struct ggml_tensor * ggml_new_tensor_1d(
            struct ggml_context * ctx,
            enum   ggml_type type,
            int64_t ne0);

    GGML_API struct ggml_tensor * ggml_new_tensor_2d(
            struct ggml_context * ctx,
            enum   ggml_type type,
            int64_t ne0,
            int64_t ne1);

    GGML_API struct ggml_tensor * ggml_new_tensor_3d(
            struct ggml_context * ctx,
            enum   ggml_type type,
            int64_t ne0,
            int64_t ne1,
            int64_t ne2);

    GGML_API struct ggml_tensor * ggml_new_tensor_4d(
            struct ggml_context * ctx,
            enum   ggml_type type,
            int64_t ne0,
            int64_t ne1,
            int64_t ne2,
            int64_t ne3);

    GGML_API struct ggml_tensor * ggml_new_i32(struct ggml_context * ctx, int32_t value);
    GGML_API struct ggml_tensor * ggml_new_f32(struct ggml_context * ctx, float value);

    GGML_API struct ggml_tensor * ggml_dup_tensor (struct ggml_context * ctx, const struct ggml_tensor * src);
    GGML_API struct ggml_tensor * ggml_view_tensor(struct ggml_context * ctx, const struct ggml_tensor * src);

    GGML_API struct ggml_tensor * ggml_get_tensor(struct ggml_context * ctx, const char * name);

    GGML_API struct ggml_tensor * ggml_set_zero(struct ggml_tensor * tensor);
    GGML_API struct ggml_tensor * ggml_set_i32 (struct ggml_tensor * tensor, int32_t value);
    GGML_API struct ggml_tensor * ggml_set_f32 (struct ggml_tensor * tensor, float value);

    GGML_API int32_t ggml_get_i32_1d(const struct ggml_tensor * tensor, int i);
    GGML_API void    ggml_set_i32_1d(const struct ggml_tensor * tensor, int i, int32_t value);

    GGML_API float   ggml_get_f32_1d(const struct ggml_tensor * tensor, int i);
    GGML_API void    ggml_set_f32_1d(const struct ggml_tensor * tensor, int i, float value);

    GGML_API void *  ggml_get_data    (const struct ggml_tensor * tensor);
    GGML_API float * ggml_get_data_f32(const struct ggml_tensor * tensor);

    GGML_API const char * ggml_get_name(const struct ggml_tensor * tensor);
    GGML_API void         ggml_set_name(struct ggml_tensor * tensor, const char * name);

    //
    // operations on tensors with backpropagation
    //

    GGML_API struct ggml_tensor * ggml_dup(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_add(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_add_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_add1(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_add1_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_acc(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b,
            size_t                nb1,
            size_t                nb2,
            size_t                nb3,
            size_t                offset);

    GGML_API struct ggml_tensor * ggml_acc_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b,
            size_t                nb1,
            size_t                nb2,
            size_t                nb3,
            size_t                offset);

    GGML_API struct ggml_tensor * ggml_sub(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_mul(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_div(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_sqr(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_sqrt(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_log(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_log_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    // return scalar
    GGML_API struct ggml_tensor * ggml_sum(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    // sums along rows, with input shape [a,b,c,d] return shape [1,b,c,d]
    GGML_API struct ggml_tensor * ggml_sum_rows(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    // mean along rows
    GGML_API struct ggml_tensor * ggml_mean(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    // if a is the same shape as b, and a is not parameter, return a
    // otherwise, return a new tensor: repeat(a) to fit in b
    GGML_API struct ggml_tensor * ggml_repeat(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_repeat_back(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_abs(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_sgn(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_neg(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_step(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_relu(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    // TODO: double-check this computation is correct
    GGML_API struct ggml_tensor * ggml_gelu(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_silu(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    // a - x
    // b - dy
    GGML_API struct ggml_tensor * ggml_silu_back(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    // normalize along rows
    // TODO: eps is hardcoded to 1e-5 for now
    GGML_API struct ggml_tensor * ggml_norm(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_rms_norm(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    // a - x
    // b - dy
    GGML_API struct ggml_tensor * ggml_rms_norm_back(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    // A: n columns, m rows
    // B: n columns, p rows  (i.e. we transpose it internally)
    // result is m columns, p rows
    GGML_API struct ggml_tensor * ggml_mul_mat(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    // A: m columns, n rows,
    // B: p columns, n rows,
    // result is m columns, p rows
    GGML_API struct ggml_tensor * ggml_out_prod(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    //
    // operations on tensors without backpropagation
    //

    GGML_API struct ggml_tensor * ggml_scale(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    // in-place, returns view(a)
    GGML_API struct ggml_tensor * ggml_scale_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    // b -> view(a,offset,nb1,nb2,3), return modified a
    GGML_API struct ggml_tensor * ggml_set(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b,
            size_t                nb1,
            size_t                nb2,
            size_t                nb3,
            size_t                offset);

    // b -> view(a,offset,nb1,nb2,3), return view(a)
    GGML_API struct ggml_tensor * ggml_set_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b,
            size_t                nb1,
            size_t                nb2,
            size_t                nb3,
            size_t                offset);

    GGML_API struct ggml_tensor * ggml_set_1d(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b,
            size_t                offset);

    GGML_API struct ggml_tensor * ggml_set_1d_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b,
            size_t                offset);

    // b -> view(a,offset,nb1,nb2,3), return modified a
    GGML_API struct ggml_tensor * ggml_set_2d(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b,
            size_t                nb1,
            size_t                offset);

    // b -> view(a,offset,nb1,nb2,3), return view(a)
    GGML_API struct ggml_tensor * ggml_set_2d_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b,
            size_t                nb1,
            size_t                offset);


    // a -> b, return view(b)
    GGML_API struct ggml_tensor * ggml_cpy(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    // make contiguous
    GGML_API struct ggml_tensor * ggml_cont(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    // return view(a), b specifies the new shape
    // TODO: when we start computing gradient, make a copy instead of view
    GGML_API struct ggml_tensor * ggml_reshape(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    // return view(a)
    // TODO: when we start computing gradient, make a copy instead of view
    GGML_API struct ggml_tensor * ggml_reshape_1d(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int64_t               ne0);

    GGML_API struct ggml_tensor * ggml_reshape_2d(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int64_t               ne0,
            int64_t               ne1);

    // return view(a)
    // TODO: when we start computing gradient, make a copy instead of view
    GGML_API struct ggml_tensor * ggml_reshape_3d(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int64_t               ne0,
            int64_t               ne1,
            int64_t               ne2);

    GGML_API struct ggml_tensor * ggml_reshape_4d(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int64_t               ne0,
            int64_t               ne1,
            int64_t               ne2,
            int64_t               ne3);

    // offset in bytes
    GGML_API struct ggml_tensor * ggml_view_1d(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int64_t               ne0,
            size_t                offset);

    GGML_API struct ggml_tensor * ggml_view_2d(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int64_t               ne0,
            int64_t               ne1,
            size_t                nb1, // row stride in bytes
            size_t                offset);

    GGML_API struct ggml_tensor * ggml_view_3d(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int64_t               ne0,
            int64_t               ne1,
            int64_t               ne2,
            size_t                nb1, // row   stride in bytes
            size_t                nb2, // slice stride in bytes
            size_t                offset);

    GGML_API struct ggml_tensor * ggml_view_4d(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int64_t               ne0,
            int64_t               ne1,
            int64_t               ne2,
            int64_t               ne3,
            size_t                nb1, // row   stride in bytes
            size_t                nb2, // slice stride in bytes
            size_t                nb3,
            size_t                offset);

    GGML_API struct ggml_tensor * ggml_permute(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int                   axis0,
            int                   axis1,
            int                   axis2,
            int                   axis3);

    // alias for ggml_permute(ctx, a, 1, 0, 2, 3)
    GGML_API struct ggml_tensor * ggml_transpose(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_get_rows(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_get_rows_back(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b,
            struct ggml_tensor  * c);

    GGML_API struct ggml_tensor * ggml_diag(
        struct ggml_context     * ctx,
        struct ggml_tensor      * a);

    // set elements above the diagonal to -INF
    GGML_API struct ggml_tensor * ggml_diag_mask_inf(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int                   n_past);

    // in-place, returns view(a)
    GGML_API struct ggml_tensor * ggml_diag_mask_inf_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int                   n_past);

    // set elements above the diagonal to 0
    GGML_API struct ggml_tensor * ggml_diag_mask_zero(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int                   n_past);

    // in-place, returns view(a)
    GGML_API struct ggml_tensor * ggml_diag_mask_zero_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int                   n_past);

    GGML_API struct ggml_tensor * ggml_soft_max(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    // in-place, returns view(a)
    GGML_API struct ggml_tensor * ggml_soft_max_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a);

    GGML_API struct ggml_tensor * ggml_soft_max_back(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    // in-place, returns view(a)
    GGML_API struct ggml_tensor * ggml_soft_max_back_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    // rotary position embedding
    // if mode & 1 == 1, skip n_past elements
    // if mode & 2 == 1, GPT-NeoX style
    // TODO: avoid creating a new tensor every time
    GGML_API struct ggml_tensor * ggml_rope(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int                   n_past,
            int                   n_dims,
            int                   mode);

    // in-place, returns view(a)
    GGML_API struct ggml_tensor * ggml_rope_inplace(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int                   n_past,
            int                   n_dims,
            int                   mode);

    // rotary position embedding backward, i.e compute dx from dy
    // a - dy
    GGML_API struct ggml_tensor * ggml_rope_back(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int                   n_past,
            int                   n_dims,
            int                   mode);

    // alibi position embedding
    // in-place, returns view(a)
    struct ggml_tensor * ggml_alibi(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            int                   n_past,
            int                   n_head,
            float                 bias_max);

    // clamp
    // in-place, returns view(a)
    struct ggml_tensor * ggml_clamp(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            float                 min,
            float                 max);

    // padding = 1
    // TODO: we don't support extra parameters for now
    //       that's why we are hard-coding the stride, padding, and dilation
    //       not great ..
    GGML_API struct ggml_tensor * ggml_conv_1d_1s(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_conv_1d_2s(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b);

    GGML_API struct ggml_tensor * ggml_flash_attn(
            struct ggml_context * ctx,
            struct ggml_tensor  * q,
            struct ggml_tensor  * k,
            struct ggml_tensor  * v,
            bool                  masked);

    GGML_API struct ggml_tensor * ggml_flash_attn_back(
           struct ggml_context * ctx,
           struct ggml_tensor  * q,
           struct ggml_tensor  * k,
           struct ggml_tensor  * v,
           struct ggml_tensor  * d,
           bool                  masked);

    GGML_API struct ggml_tensor * ggml_flash_ff(
            struct ggml_context * ctx,
            struct ggml_tensor  * a,
            struct ggml_tensor  * b0,
            struct ggml_tensor  * b1,
            struct ggml_tensor  * c0,
            struct ggml_tensor  * c1);

    // Mapping operations
    typedef void (*ggml_unary_op_f32_t)(const int, float *, const float *);
    typedef void (*ggml_binary_op_f32_t)(const int, float *, const float *, const float *);

    GGML_API struct ggml_tensor * ggml_map_unary_f32(
            struct ggml_context        * ctx,
            struct ggml_tensor         * a,
                   ggml_unary_op_f32_t   fun);

    GGML_API struct ggml_tensor * ggml_map_binary_f32(
            struct ggml_context         * ctx,
            struct ggml_tensor          * a,
            struct ggml_tensor          * b,
                   ggml_binary_op_f32_t   fun);

    // loss function

    GGML_API struct ggml_tensor * ggml_cross_entropy_loss(
            struct ggml_context         * ctx,
            struct ggml_tensor          * a,
            struct ggml_tensor          * b);

    GGML_API struct ggml_tensor * ggml_cross_entropy_loss_back(
            struct ggml_context         * ctx,
            struct ggml_tensor          * a,
            struct ggml_tensor          * b,
            struct ggml_tensor          * c);

    //
    // automatic differentiation
    //

    GGML_API void ggml_set_param(
            struct ggml_context * ctx,
            struct ggml_tensor * tensor);

    GGML_API void ggml_build_forward_expand(struct ggml_cgraph * cgraph, struct ggml_tensor * tensor);

    GGML_API struct ggml_cgraph ggml_build_forward (struct ggml_tensor * tensor);
    GGML_API struct ggml_cgraph ggml_build_backward(struct ggml_context * ctx, struct ggml_cgraph * gf, bool keep);

    GGML_API void ggml_graph_compute(struct ggml_context * ctx, struct ggml_cgraph * cgraph);
    GGML_API void ggml_graph_reset  (struct ggml_cgraph * cgraph);

    GGML_API struct ggml_tensor * ggml_graph_get_tensor(struct ggml_cgraph * cgraph, const char * name);

    GGML_API void               ggml_graph_export(const struct ggml_cgraph * cgraph, const char * fname);
    GGML_API struct ggml_cgraph ggml_graph_import(const char * fname, struct ggml_context ** ctx_data, struct ggml_context ** ctx_eval);

    // print info and performance information for the graph
    GGML_API void ggml_graph_print(const struct ggml_cgraph * cgraph);

    // dump the graph into a file using the dot format
    GGML_API void ggml_graph_dump_dot(const struct ggml_cgraph * gb, const struct ggml_cgraph * gf, const char * filename);

    //
    // optimization
    //

    // optimization methods
    enum ggml_opt_type {
        GGML_OPT_ADAM,
        GGML_OPT_LBFGS,
    };

    // linesearch methods
    enum ggml_linesearch {
        GGML_LINESEARCH_DEFAULT = 1,

        GGML_LINESEARCH_BACKTRACKING_ARMIJO       = 0,
        GGML_LINESEARCH_BACKTRACKING_WOLFE        = 1,
        GGML_LINESEARCH_BACKTRACKING_STRONG_WOLFE = 2,
    };

    // optimization return values
    enum ggml_opt_result {
        GGML_OPT_OK = 0,
        GGML_OPT_DID_NOT_CONVERGE,
        GGML_OPT_NO_CONTEXT,
        GGML_OPT_INVALID_WOLFE,
        GGML_OPT_FAIL,

        GGML_LINESEARCH_FAIL = -128,
        GGML_LINESEARCH_MINIMUM_STEP,
        GGML_LINESEARCH_MAXIMUM_STEP,
        GGML_LINESEARCH_MAXIMUM_ITERATIONS,
        GGML_LINESEARCH_INVALID_PARAMETERS,
    };

    // optimization parameters
    //
    //   see ggml.c (ggml_opt_default_params) for default values
    //
    struct ggml_opt_params {
        enum ggml_opt_type type;

        int n_threads;

        // delta-based convergence test
        //
        //   if past == 0 - disabled
        //   if past > 0:
        //     stop if |f(x) - f(x_past)| < delta * max(1, |f(x)|)
        //
        int past;
        float delta;

        // maximum number of iterations without improvement
        //
        //   if 0 - disabled
        //   if > 0:
        //     assume convergence if no cost improvement in this number of iterations
        //
        int max_no_improvement;

        bool print_forward_graph;
        bool print_backward_graph;

        // ADAM parameters
        struct {
            int n_iter;

            float sched; // schedule multiplier (fixed, decay or warmup)
            float decay; // weight decay for AdamW, use 0.0f to disable
            float alpha; // learning rate
            float beta1;
            float beta2;
            float eps;   // epsilon for numerical stability
            float eps_f; // epsilon for convergence test
            float eps_g; // epsilon for convergence test
        } adam;

        // LBFGS parameters
        struct {
            int m; // number of corrections to approximate the inv. Hessian
            int n_iter;
            int max_linesearch;

            float eps;      // convergence tolerance
            float ftol;     // line search tolerance
            float wolfe;
            float min_step;
            float max_step;

            enum ggml_linesearch linesearch;
        } lbfgs;
    };

    struct ggml_opt_context {
        struct ggml_context * ctx;
        struct ggml_opt_params params;

        int iter;
        int64_t nx; // number of parameter elements

        bool just_initialized;

        struct {
            struct ggml_tensor * x;  // view of the parameters
            struct ggml_tensor * g1; // gradient
            struct ggml_tensor * g2; // gradient squared
            struct ggml_tensor * m;  // first moment
            struct ggml_tensor * v;  // second moment
            struct ggml_tensor * mh; // first moment hat
            struct ggml_tensor * vh; // second moment hat
            struct ggml_tensor * pf; // past function values
            float fx_best;
            float fx_prev;
            int n_no_improvement;
        } adam;

        struct {
            struct ggml_tensor * x;    // current parameters
            struct ggml_tensor * xp;   // previous parameters
            struct ggml_tensor * g;    // current gradient
            struct ggml_tensor * gp;   // previous gradient
            struct ggml_tensor * d;    // search direction
            struct ggml_tensor * pf;   // past function values
            struct ggml_tensor * lmal; // the L-BFGS memory alpha
            struct ggml_tensor * lmys; // the L-BFGS memory ys
            struct ggml_tensor * lms;  // the L-BFGS memory s
            struct ggml_tensor * lmy;  // the L-BFGS memory y
            float fx_best;
            float step;
            int j;
            int k;
            int end;
            int n_no_improvement;
        } lbfgs;
    };

    GGML_API struct ggml_opt_params ggml_opt_default_params(enum ggml_opt_type type);

    // optimize the function defined by the tensor f
    GGML_API enum ggml_opt_result ggml_opt(
            struct ggml_context * ctx,
            struct ggml_opt_params params,
            struct ggml_tensor * f);

    // initialize optimizer context
    GGML_API void ggml_opt_init(
            struct ggml_context * ctx,
            struct ggml_opt_context * opt,
            struct ggml_opt_params params,
            int64_t nx);

    // continue optimizing the function defined by the tensor f
    GGML_API enum ggml_opt_result ggml_opt_resume(
            struct ggml_context * ctx,
            struct ggml_opt_context * opt,
            struct ggml_tensor * f);

    // continue optimizing the function defined by the tensor f
    GGML_API enum ggml_opt_result ggml_opt_resume_g(
            struct ggml_context * ctx,
            struct ggml_opt_context * opt,
            struct ggml_tensor * f,
            struct ggml_cgraph * gf,
            struct ggml_cgraph * gb);

    //
    // quantization
    //

    GGML_API size_t ggml_quantize_q4_0(const float * src, void * dst, int n, int k, int64_t * hist);
    GGML_API size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t * hist);
    GGML_API size_t ggml_quantize_q5_0(const float * src, void * dst, int n, int k, int64_t * hist);
    GGML_API size_t ggml_quantize_q5_1(const float * src, void * dst, int n, int k, int64_t * hist);
    GGML_API size_t ggml_quantize_q8_0(const float * src, void * dst, int n, int k, int64_t * hist);

    GGML_API size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, int start, int n, int64_t * hist);

    //
    // system info
    //

    GGML_API int ggml_cpu_has_avx        (void);
    GGML_API int ggml_cpu_has_avx2       (void);
    GGML_API int ggml_cpu_has_avx512     (void);
    GGML_API int ggml_cpu_has_avx512_vbmi(void);
    GGML_API int ggml_cpu_has_avx512_vnni(void);
    GGML_API int ggml_cpu_has_fma        (void);
    GGML_API int ggml_cpu_has_neon       (void);
    GGML_API int ggml_cpu_has_arm_fma    (void);
    GGML_API int ggml_cpu_has_f16c       (void);
    GGML_API int ggml_cpu_has_fp16_va    (void);
    GGML_API int ggml_cpu_has_wasm_simd  (void);
    GGML_API int ggml_cpu_has_blas       (void);
    GGML_API int ggml_cpu_has_cublas     (void);
    GGML_API int ggml_cpu_has_clblast    (void);
    GGML_API int ggml_cpu_has_gpublas    (void);
    GGML_API int ggml_cpu_has_sse3       (void);
    GGML_API int ggml_cpu_has_vsx        (void);

    //
    // Internal types and functions exposed for tests and benchmarks
    //

#ifdef  __cplusplus
    // restrict not standard in C++
#define GGML_RESTRICT
#else
#define GGML_RESTRICT restrict
#endif
    typedef void (*dequantize_row_q_t)(const void * GGML_RESTRICT x, float * GGML_RESTRICT y, int k);
    typedef void (*quantize_row_q_t)  (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int k);
    typedef void (*vec_dot_q_t)       (const int n, float * GGML_RESTRICT s, const void * GGML_RESTRICT x, const void * GGML_RESTRICT y);

    typedef struct {
        dequantize_row_q_t dequantize_row_q;
        quantize_row_q_t   quantize_row_q;
        quantize_row_q_t   quantize_row_q_reference;
        quantize_row_q_t   quantize_row_q_dot;
        vec_dot_q_t        vec_dot_q;
        enum ggml_type     vec_dot_type;
    } quantize_fns_t;

    quantize_fns_t ggml_internal_get_quantize_fn(size_t i);

#ifdef  __cplusplus
}
#endif