-
Notifications
You must be signed in to change notification settings - Fork 4
/
llama.cpp
1856 lines (1493 loc) · 58.9 KB
/
llama.cpp
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
#include "llama.h"
#include "ggml.h"
#include <cinttypes>
#include <fstream>
#include <random>
#include <map>
#include <unordered_map>
#include <queue>
#include <regex>
#include <cassert>
#include <cstring>
#if defined(_WIN32) && !defined(_POSIX_MAPPED_FILES)
#define WIN32_LEAN_AND_MEAN
#include <Windows.h>
#else
#include <sys/types.h>
#include <sys/mman.h>
#include <unistd.h>
#include <fcntl.h>
#endif
#define Min(X, Y) ((Y) > (X) ? (X) : (Y))
#define Max(X, Y) ((Y) < (X) ? (X) : (Y))
#define LLAMA_USE_SCRATCH
#define LLAMA_MAX_SCRATCH_BUFFERS 16
#define LLAMA_ASSERT(x) \
do { \
if (!(x)) { \
fprintf(stderr, "LLAMA_ASSERT: %s:%d: %s\n", __FILE__, __LINE__, #x); \
abort(); \
} \
} while (0)
// determine number of model parts based on the dimension
static const std::unordered_map<int, int> LLAMA_N_PARTS = {
{ 4096, 1 },
{ 5120, 2 },
{ 6656, 4 },
{ 8192, 8 },
};
// available llama models
enum e_model {
MODEL_UNKNOWN,
MODEL_7B,
MODEL_13B,
MODEL_30B,
MODEL_65B,
};
static const size_t MB = 1024*1024;
// computed for n_ctx == 2048
// TODO: dynamically determine these sizes
// needs modifications in ggml
static const std::map<e_model, size_t> MEM_REQ_SCRATCH0 = {
{ MODEL_7B, 512ull*MB },
{ MODEL_13B, 512ull*MB },
{ MODEL_30B, 512ull*MB },
{ MODEL_65B, 512ull*MB },
};
static const std::map<e_model, size_t> MEM_REQ_SCRATCH1 = {
{ MODEL_7B, 512ull*MB },
{ MODEL_13B, 512ull*MB },
{ MODEL_30B, 512ull*MB },
{ MODEL_65B, 512ull*MB },
};
// 2*n_embd*n_ctx*n_layer*sizeof(float16)
static const std::map<e_model, size_t> MEM_REQ_KV_SELF = {
{ MODEL_7B, 1026ull*MB },
{ MODEL_13B, 1608ull*MB },
{ MODEL_30B, 3124ull*MB },
{ MODEL_65B, 5120ull*MB },
};
// this is mostly needed for temporary mul_mat buffers to dequantize the data
// not actually needed if BLAS is disabled
static const std::map<e_model, size_t> MEM_REQ_EVAL = {
{ MODEL_7B, 768ull*MB },
{ MODEL_13B, 1024ull*MB },
{ MODEL_30B, 1280ull*MB },
{ MODEL_65B, 1536ull*MB },
};
// default hparams (LLaMA 7B)
struct llama_hparams {
int32_t n_vocab = 32000;
int32_t n_ctx = 512; // this is provided as user input?
int32_t n_embd = 4096;
int32_t n_mult = 256;
int32_t n_head = 32;
int32_t n_layer = 32;
int32_t n_rot = 64;
int32_t f16 = 1;
};
struct llama_layer {
// normalization
struct ggml_tensor * attention_norm;
// attention
struct ggml_tensor * wq;
struct ggml_tensor * wk;
struct ggml_tensor * wv;
struct ggml_tensor * wo;
// normalization
struct ggml_tensor * ffn_norm;
// ff
struct ggml_tensor * w1;
struct ggml_tensor * w2;
struct ggml_tensor * w3;
};
struct llama_kv_cache {
struct ggml_tensor * k;
struct ggml_tensor * v;
struct ggml_context * ctx;
std::vector<uint8_t> buf;
int n; // number of tokens currently in the cache
};
struct llama_model {
e_model type = MODEL_UNKNOWN;
llama_hparams hparams;
struct ggml_tensor * tok_embeddings;
struct ggml_tensor * norm;
struct ggml_tensor * output;
std::vector<llama_layer> layers;
// context
struct ggml_context * ctx;
// key + value cache for the self attention
// TODO: move to llama_state
struct llama_kv_cache kv_self;
// the model memory buffer
std::vector<uint8_t> buf;
// model memory mapped file
void * mm_addr = NULL;
uint64_t mm_length = 0;
// tensors
int n_loaded;
std::unordered_map<std::string, struct ggml_tensor *> tensors;
};
struct llama_vocab {
using id = int32_t;
using token = std::string;
struct token_score {
token tok;
float score;
};
std::unordered_map<token, id> token_to_id;
std::vector<token_score> id_to_token;
};
struct llama_context {
std::mt19937 rng;
int64_t t_load_us = 0;
int64_t t_start_us = 0;
bool has_evaluated_once = false;
int64_t t_sample_us = 0;
int64_t t_eval_us = 0;
int64_t t_p_eval_us = 0;
int32_t n_sample = 0; // number of tokens sampled
int32_t n_eval = 0; // number of eval calls
int32_t n_p_eval = 0; // number of tokens in eval calls for the prompt (with batch size > 1)
llama_model model;
llama_vocab vocab;
size_t mem_per_token = 0;
// decode output (2-dimensional array: [n_tokens][n_vocab])
std::vector<float> logits;
bool logits_all = false;
// input embedding (1-dimensional array: [n_embd])
std::vector<float> embedding;
// memory buffers used to evaluate the model
// TODO: move in llama_state
std::vector<uint8_t> buf_compute;
std::vector<uint8_t> buf_scratch[LLAMA_MAX_SCRATCH_BUFFERS];
int buf_last = 0;
size_t buf_max_size[LLAMA_MAX_SCRATCH_BUFFERS] = { 0 };
void use_buf(struct ggml_context * ctx, int i) {
#if defined(LLAMA_USE_SCRATCH)
size_t last_size = 0;
if (i == -1) {
last_size = ggml_set_scratch(ctx, { 0, 0, nullptr, });
} else {
auto & buf = buf_scratch[i];
last_size = ggml_set_scratch(ctx, { 0, buf.size(), buf.data(), });
}
if (buf_last >= 0) {
buf_max_size[buf_last] = Max(buf_max_size[buf_last], last_size);
}
buf_last = i;
#else
(void) i;
(void) ctx;
#endif
}
size_t get_buf_max_mem(int i) const {
#if defined(LLAMA_USE_SCRATCH)
return buf_max_size[i];
#else
(void) i;
return 0;
#endif
}
};
//
// kv cache
//
static bool kv_cache_init(
const struct llama_hparams & hparams,
struct llama_kv_cache & cache,
ggml_type wtype,
int n_ctx) {
const int n_embd = hparams.n_embd;
const int n_layer = hparams.n_layer;
const int64_t n_mem = (int64_t)n_layer*n_ctx;
const int64_t n_elements = n_embd*n_mem;
cache.buf.resize(2u*n_elements*ggml_type_size(wtype) + 2u*MB);
struct ggml_init_params params;
params.mem_size = cache.buf.size();
params.mem_buffer = cache.buf.data();
params.no_alloc = false;
cache.ctx = ggml_init(params);
if (!cache.ctx) {
fprintf(stderr, "%s: failed to allocate memory for kv cache\n", __func__);
return false;
}
cache.k = ggml_new_tensor_1d(cache.ctx, wtype, n_elements);
cache.v = ggml_new_tensor_1d(cache.ctx, wtype, n_elements);
return true;
}
static void kv_cache_free(struct llama_kv_cache & cache) {
if (cache.ctx) {
ggml_free(cache.ctx);
cache.ctx = nullptr;
}
}
struct llama_context_params llama_context_default_params() {
struct llama_context_params result = {
/*.n_ctx =*/ 512,
/*.n_parts =*/ -1,
/*.seed =*/ 0,
/*.f16_kv =*/ false,
/*.logits_all =*/ false,
/*.vocab_only =*/ false,
/*.use_mlock =*/ false,
/*.embedding =*/ false,
/*.progress_callback =*/ nullptr,
/*.progress_callback_user_data =*/ nullptr,
};
return result;
}
//
// model loading
//
static void *mmap_file(const char *fname, uint64_t *mm_length) {
#if defined(_WIN32) && !defined(_POSIX_MAPPED_FILES)
HANDLE hFile = CreateFileA(fname,
GENERIC_READ,
FILE_SHARE_READ | FILE_SHARE_WRITE | FILE_SHARE_DELETE,
NULL,
OPEN_EXISTING,
FILE_ATTRIBUTE_NORMAL | FILE_ATTRIBUTE_NOT_CONTENT_INDEXED,
NULL);
if (hFile == INVALID_HANDLE_VALUE) return 0;
LARGE_INTEGER fileSize;
fileSize.QuadPart = -1;
GetFileSizeEx(hFile, &fileSize);
int64_t length = fileSize.QuadPart;
HANDLE hMapping = CreateFileMappingA(hFile, NULL, PAGE_READONLY, 0, 0, NULL);
CloseHandle(hFile);
if (!hMapping) return 0;
void *addr = MapViewOfFile(hMapping, FILE_MAP_READ, 0, 0, 0);
CloseHandle(hMapping);
if (!addr) return 0;
#else
int fd = open(fname, O_RDONLY);
if (fd == -1) return 0;
int64_t length = lseek(fd, 0, SEEK_END);
void *addr = mmap(NULL, length, PROT_READ, MAP_SHARED, fd, 0);
close(fd);
if (addr == MAP_FAILED) return 0;
#endif
*mm_length = length;
return addr;
}
static void munmap_file(void * addr, size_t length) {
#if defined(_WIN32) && !defined(_POSIX_MAPPED_FILES)
UnmapViewOfFile(addr);
#else
munmap(addr, length);
#endif
}
static bool report_bad_magic(const char *path, uint32_t got, uint32_t want) {
fprintf(stderr,
"%s: invalid model file (bad magic [got %#x want %#x])\n"
"\tyou most likely need to regenerate your ggml files\n"
"\tthe benefit is you'll get 10-100x faster load times\n"
"\tsee https://github.com/ggerganov/llama.cpp/issues/91\n"
"\tuse convert-pth-to-ggml.py to regenerate from original pth\n"
"\tuse migrate-ggml-2023-03-30-pr613.py if you deleted originals\n",
path, got, want);
return false;
}
static bool llama_model_load(
const std::string & fname,
llama_context & lctx,
int n_ctx,
int n_parts,
ggml_type memory_type,
bool vocab_only,
llama_progress_callback progress_callback,
void *progress_callback_user_data) {
fprintf(stderr, "%s: loading model from '%s' - please wait ...\n", __func__, fname.c_str());
lctx.t_start_us = ggml_time_us();
auto & model = lctx.model;
auto & vocab = lctx.vocab;
auto fin = std::ifstream(fname, std::ios::binary);
if (!fin) {
fprintf(stderr, "%s: failed to open '%s'\n", __func__, fname.c_str());
return false;
}
std::vector<char> f_buf(1024*1024);
fin.rdbuf()->pubsetbuf(f_buf.data(), f_buf.size());
fin.seekg(0, fin.end);
const size_t file_size = fin.tellg();
fin.seekg(0);
// verify magic
{
uint32_t magic;
fin.read((char *) &magic, sizeof(magic));
if (magic == LLAMA_FILE_MAGIC_UNVERSIONED) {
fprintf(stderr, "%s: invalid model file '%s' (too old, regenerate your model files or convert them with convert-unversioned-ggml-to-ggml.py!)\n",
__func__, fname.c_str());
return false;
}
if (magic != LLAMA_FILE_MAGIC) {
return report_bad_magic(fname.c_str(), magic, LLAMA_FILE_MAGIC);
}
uint32_t format_version;
fin.read((char *) &format_version, sizeof(format_version));
if (format_version != LLAMA_FILE_VERSION) {
fprintf(stderr, "%s: invalid model file '%s' (unsupported format version %" PRIu32 ", expected %d)\n",
__func__, fname.c_str(), format_version, LLAMA_FILE_VERSION);
return false;
}
}
int n_ff = 0;
// load hparams
{
auto & hparams = model.hparams;
fin.read((char *) &hparams.n_vocab, sizeof(hparams.n_vocab));
//fin.read((char *) &hparams.n_ctx, sizeof(hparams.n_ctx));
fin.read((char *) &hparams.n_embd, sizeof(hparams.n_embd));
fin.read((char *) &hparams.n_mult, sizeof(hparams.n_mult));
fin.read((char *) &hparams.n_head, sizeof(hparams.n_head));
fin.read((char *) &hparams.n_layer, sizeof(hparams.n_layer));
fin.read((char *) &hparams.n_rot, sizeof(hparams.n_rot));
fin.read((char *) &hparams.f16, sizeof(hparams.f16));
hparams.n_ctx = n_ctx;
n_ff = ((2*(4*hparams.n_embd)/3 + hparams.n_mult - 1)/hparams.n_mult)*hparams.n_mult;
if (n_parts < 1) {
n_parts = LLAMA_N_PARTS.at(hparams.n_embd);
}
// temp warning to tell the user to use "--n_parts"
if (hparams.f16 == 4 && n_parts != 1) {
fprintf(stderr, "%s: GPTQ model detected - are you sure n_parts should be %d? we normally expect it to be 1\n", __func__, n_parts);
fprintf(stderr, "%s: use '--n_parts 1' if necessary\n", __func__);
}
if (hparams.n_layer == 32) {
model.type = e_model::MODEL_7B;
}
if (hparams.n_layer == 40) {
model.type = e_model::MODEL_13B;
}
if (hparams.n_layer == 60) {
model.type = e_model::MODEL_30B;
}
if (hparams.n_layer == 80) {
model.type = e_model::MODEL_65B;
}
fprintf(stderr, "%s: n_vocab = %d\n", __func__, hparams.n_vocab);
fprintf(stderr, "%s: n_ctx = %d\n", __func__, hparams.n_ctx);
fprintf(stderr, "%s: n_embd = %d\n", __func__, hparams.n_embd);
fprintf(stderr, "%s: n_mult = %d\n", __func__, hparams.n_mult);
fprintf(stderr, "%s: n_head = %d\n", __func__, hparams.n_head);
fprintf(stderr, "%s: n_layer = %d\n", __func__, hparams.n_layer);
fprintf(stderr, "%s: n_rot = %d\n", __func__, hparams.n_rot);
fprintf(stderr, "%s: f16 = %d\n", __func__, hparams.f16);
fprintf(stderr, "%s: n_ff = %d\n", __func__, n_ff);
fprintf(stderr, "%s: n_parts = %d\n", __func__, n_parts);
fprintf(stderr, "%s: type = %d\n", __func__, model.type);
}
// load vocab
{
std::string word;
vocab.id_to_token.resize(model.hparams.n_vocab);
std::vector<char> tmp(64);
for (int i = 0; i < model.hparams.n_vocab; i++) {
uint32_t len;
fin.read((char *) &len, sizeof(len));
word.resize(len);
if (len > 0) {
tmp.resize(len);
fin.read(tmp.data(), len);
word.assign(tmp.data(), len);
} else {
word.clear();
}
float score;
fin.read((char *) &score, sizeof(score));
vocab.token_to_id[word] = i;
auto &tok_score = vocab.id_to_token[i];
tok_score.tok = word;
tok_score.score = score;
}
}
if (vocab_only) {
return true;
}
// for the big tensors, we have the option to store the data in 16-bit floats or quantized
// in order to save memory and also to speed up the computation
// wtype is for per-layer weights, while vtype is for other weights
ggml_type wtype, vtype;
switch (model.hparams.f16) {
case 0: wtype = vtype = GGML_TYPE_F32; break;
case 1: wtype = vtype = GGML_TYPE_F16; break;
case 2: wtype = vtype = GGML_TYPE_Q4_0; break;
case 3: wtype = vtype = GGML_TYPE_Q4_1; break;
case 4: wtype = GGML_TYPE_Q4_1; vtype = GGML_TYPE_F16; break;
default:
{
fprintf(stderr, "%s: invalid model file '%s' (bad f16 value %d)\n",
__func__, fname.c_str(), model.hparams.f16);
return false;
}
}
// map model into memory
char *mm_addr = NULL;
model.mm_addr = mmap_file(fname.c_str(), &model.mm_length);
if (model.mm_addr == NULL) {
fprintf(stderr, "%s: failed to mmap '%s'\n", __func__, fname.c_str());
return false;
}
mm_addr = (char *)model.mm_addr;
fprintf(stderr, "%s: ggml map size = %6.2f MB\n", __func__, model.mm_length/(1024.0*1024.0));
auto & ctx = model.ctx;
size_t ctx_size = 0;
{
const auto &hparams = model.hparams;
const int n_layer = hparams.n_layer;
ctx_size += (5 + 10*n_layer)*256; // object overhead
fprintf(stderr, "%s: ggml ctx size = %6.2f KB\n", __func__, ctx_size/1024.0);
}
// print memory requirements
{
const size_t scale = memory_type == GGML_TYPE_F32 ? 2 : 1;
// this is the total memory required to run the inference
const size_t mem_required =
ctx_size +
model.mm_length +
MEM_REQ_SCRATCH0.at(model.type) +
MEM_REQ_SCRATCH1.at(model.type) +
MEM_REQ_EVAL.at (model.type);
// this is the memory required by one llama_state
const size_t mem_required_state =
scale*MEM_REQ_KV_SELF.at(model.type);
fprintf(stderr, "%s: mem required = %7.2f MB (+ %7.2f MB per state)\n", __func__,
mem_required / 1024.0 / 1024.0, mem_required_state / 1024.0 / 1024.0);
}
// create the ggml context
{
lctx.model.buf.resize(ctx_size);
struct ggml_init_params params = {
/*.mem_size =*/ lctx.model.buf.size(),
/*.mem_buffer =*/ lctx.model.buf.data(),
/*.no_alloc =*/ true,
};
model.ctx = ggml_init(params);
if (!model.ctx) {
fprintf(stderr, "%s: ggml_init() failed\n", __func__);
return false;
}
}
// prepare memory for the weights
{
const auto & hparams = model.hparams;
const int n_embd = hparams.n_embd;
const int n_layer = hparams.n_layer;
const int n_vocab = hparams.n_vocab;
model.layers.resize(n_layer);
model.tok_embeddings = ggml_new_tensor_2d(ctx, vtype, n_embd, n_vocab);
model.norm = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, n_embd);
model.output = ggml_new_tensor_2d(ctx, vtype, n_embd, n_vocab);
// map by name
model.tensors["tok_embeddings.weight"] = model.tok_embeddings;
model.tensors["norm.weight"] = model.norm;
model.tensors["output.weight"] = model.output;
for (int i = 0; i < n_layer; ++i) {
auto & layer = model.layers[i];
layer.attention_norm = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, n_embd);
layer.wq = ggml_new_tensor_2d(ctx, wtype, n_embd, n_embd);
layer.wk = ggml_new_tensor_2d(ctx, wtype, n_embd, n_embd);
layer.wv = ggml_new_tensor_2d(ctx, wtype, n_embd, n_embd);
layer.wo = ggml_new_tensor_2d(ctx, wtype, n_embd, n_embd);
layer.ffn_norm = ggml_new_tensor_1d(ctx, GGML_TYPE_F32, n_embd);
layer.w1 = ggml_new_tensor_2d(ctx, wtype, n_embd, n_ff);
layer.w2 = ggml_new_tensor_2d(ctx, wtype, n_ff, n_embd);
layer.w3 = ggml_new_tensor_2d(ctx, wtype, n_embd, n_ff);
// map by name
model.tensors["layers." + std::to_string(i) + ".attention_norm.weight"] = layer.attention_norm;
model.tensors["layers." + std::to_string(i) + ".attention.wq.weight"] = layer.wq;
model.tensors["layers." + std::to_string(i) + ".attention.wk.weight"] = layer.wk;
model.tensors["layers." + std::to_string(i) + ".attention.wv.weight"] = layer.wv;
model.tensors["layers." + std::to_string(i) + ".attention.wo.weight"] = layer.wo;
model.tensors["layers." + std::to_string(i) + ".ffn_norm.weight"] = layer.ffn_norm;
model.tensors["layers." + std::to_string(i) + ".feed_forward.w1.weight"] = layer.w1;
model.tensors["layers." + std::to_string(i) + ".feed_forward.w2.weight"] = layer.w2;
model.tensors["layers." + std::to_string(i) + ".feed_forward.w3.weight"] = layer.w3;
}
}
std::vector<uint8_t> tmp;
if (progress_callback) {
progress_callback(0.0, progress_callback_user_data);
}
fprintf(stderr, "%s: loading tensors from '%s'\n", __func__, fname.c_str());
// load weights
{
size_t total_size = 0;
model.n_loaded = 0;
while (true) {
int32_t n_dims;
int32_t length;
int32_t ftype;
fin.read(reinterpret_cast<char *>(&n_dims), sizeof(n_dims));
fin.read(reinterpret_cast<char *>(&length), sizeof(length));
fin.read(reinterpret_cast<char *>(&ftype), sizeof(ftype));
if (fin.eof()) {
break;
}
int32_t nelements = 1;
int32_t ne[2] = { 1, 1 };
for (int i = 0; i < n_dims; ++i) {
fin.read(reinterpret_cast<char *>(&ne[i]), sizeof(ne[i]));
nelements *= ne[i];
}
std::string name(length, 0);
fin.read(&name[0], length);
if (model.tensors.find(name.data()) == model.tensors.end()) {
fprintf(stderr, "%s: unknown tensor '%s' in model file\n", __func__, name.data());
return false;
}
auto tensor = model.tensors[name.data()];
if (ggml_nelements(tensor) != nelements) {
fprintf(stderr, "%s: tensor '%s' has wrong size in model file\n", __func__, name.data());
return false;
}
if (tensor->ne[0] != ne[0] || tensor->ne[1] != ne[1]) {
fprintf(stderr, "%s: tensor '%s' has wrong shape in model file: got [%" PRId64 ", %" PRId64 "], expected [%d, %d]\n",
__func__, name.data(), tensor->ne[0], tensor->ne[1], ne[0], ne[1]);
return false;
}
if (0) {
static const char * ftype_str[] = { "f32", "f16", "q4_0", "q4_1", };
fprintf(stderr, "%24s - [%5d, %5d], type = %6s\n", name.data(), ne[0], ne[1], ftype_str[ftype]);
}
switch (ftype) {
case 0: // f32
case 1: // f16
break;
case 2: // q4_0
case 3: // q4_1
assert(ne[0] % 64 == 0);
break;
default:
fprintf(stderr, "%s: unknown ftype %d in model file\n", __func__, ftype);
return false;
};
// load the tensor data into memory without copying or reading it
size_t offset = fin.tellg();
size_t tensor_data_size = ggml_nbytes(tensor);
offset = (offset + 31) & -32;
tensor->data = mm_addr + offset;
fin.seekg(offset + tensor_data_size);
total_size += tensor_data_size;
model.n_loaded++;
// progress
if (progress_callback) {
double current_progress = size_t(fin.tellg()) / double(file_size);
progress_callback(current_progress, progress_callback_user_data);
}
}
fin.close();
fprintf(stderr, "%s: model size = %8.2f MB / num tensors = %d\n", __func__, total_size/1024.0/1024.0, model.n_loaded);
if (model.n_loaded == 0) {
fprintf(stderr, "%s: WARN no tensors loaded from model file - assuming empty model for testing\n", __func__);
} else if (model.n_loaded != (int) model.tensors.size()) {
fprintf(stderr, "%s: ERROR not all tensors loaded from model file - expected %zu, got %d\n", __func__, model.tensors.size(), model.n_loaded);
return false;
}
}
// loading time will be recalculate after the first eval, so
// we take page faults deferred by mmap() into consideration
lctx.t_load_us = ggml_time_us() - lctx.t_start_us;
if (progress_callback) {
progress_callback(1.0, progress_callback_user_data);
}
return true;
}
// evaluate the transformer
//
// - lctx: llama context
// - tokens: new batch of tokens to process
// - n_past: the context size so far
// - n_threads: number of threads to use
//
static bool llama_eval_internal(
llama_context & lctx,
const llama_token * tokens,
const int n_tokens,
const int n_past,
const int n_threads) {
const int64_t t_start_us = ggml_time_us();
const int N = n_tokens;
const auto & model = lctx.model;
const auto & hparams = model.hparams;
auto & kv_self = model.kv_self;
LLAMA_ASSERT(!!kv_self.ctx);
const int n_embd = hparams.n_embd;
const int n_layer = hparams.n_layer;
const int n_ctx = hparams.n_ctx;
const int n_head = hparams.n_head;
const int n_vocab = hparams.n_vocab;
const int n_rot = hparams.n_embd/hparams.n_head;
auto & mem_per_token = lctx.mem_per_token;
auto & buf_compute = lctx.buf_compute;
struct ggml_init_params params = {
/*.mem_size =*/ buf_compute.size(),
/*.mem_buffer =*/ buf_compute.data(),
/*.no_alloc =*/ false,
};
struct ggml_context * ctx0 = ggml_init(params);
// for big prompts, if BLAS is enabled, it is better to use only one thread
// otherwise, the threads are spin-lock waiting for the BLAS calls and are degrading the performance
ggml_cgraph gf = {};
gf.n_threads = N >= 32 && ggml_cpu_has_blas() ? 1 : n_threads;
struct ggml_tensor * embd = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N);
memcpy(embd->data, tokens, N*ggml_element_size(embd));
struct ggml_tensor * inpL = ggml_get_rows(ctx0, model.tok_embeddings, embd);
for (int il = 0; il < n_layer; ++il) {
struct ggml_tensor * inpSA = inpL;
struct ggml_tensor * cur;
lctx.use_buf(ctx0, 0);
// norm
{
cur = ggml_rms_norm(ctx0, inpL);
// cur = attention_norm*cur
cur = ggml_mul(ctx0,
ggml_repeat(ctx0, model.layers[il].attention_norm, cur),
cur);
}
// self-attention
{
struct ggml_tensor * Qcur = ggml_mul_mat(ctx0, model.layers[il].wq, cur);
struct ggml_tensor * Kcur = ggml_mul_mat(ctx0, model.layers[il].wk, cur);
struct ggml_tensor * Vcur = ggml_mul_mat(ctx0, model.layers[il].wv, cur);
// store key and value to memory
if (N >= 1) {
struct ggml_tensor * k = ggml_view_1d(ctx0, kv_self.k, N*n_embd, (ggml_element_size(kv_self.k)*n_embd)*(il*n_ctx + n_past));
struct ggml_tensor * v = ggml_view_1d(ctx0, kv_self.v, N*n_embd, (ggml_element_size(kv_self.v)*n_embd)*(il*n_ctx + n_past));
ggml_build_forward_expand(&gf, ggml_cpy(ctx0, Kcur, k));
ggml_build_forward_expand(&gf, ggml_cpy(ctx0, Vcur, v));
}
// Q = Qcur.contiguous().view(n_embd/n_head, n_head, N).permute(0, 2, 1, 3)
struct ggml_tensor * Q =
ggml_permute(ctx0,
ggml_rope(ctx0,
ggml_cpy(ctx0,
Qcur,
ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_embd/n_head, n_head, N)),
n_past, n_rot, 0),
0, 2, 1, 3);
// K = Kmem.view(n_embd/n_head, n_head, n_past + N).permute(0, 2, 1, 3)
struct ggml_tensor * K =
ggml_permute(ctx0,
ggml_rope(ctx0,
ggml_reshape_3d(ctx0,
ggml_view_1d(ctx0, kv_self.k, (n_past + N)*n_embd, il*n_ctx*ggml_element_size(kv_self.k)*n_embd),
n_embd/n_head, n_head, n_past + N),
n_past, n_rot, 1),
0, 2, 1, 3);
// K * Q
struct ggml_tensor * KQ = ggml_mul_mat(ctx0, K, Q);
// KQ_scaled = KQ / sqrt(n_embd/n_head)
struct ggml_tensor * KQ_scaled =
ggml_scale(ctx0,
KQ,
ggml_new_f32(ctx0, 1.0f/sqrtf(float(n_embd)/n_head)));
// KQ_masked = mask_past(KQ_scaled)
struct ggml_tensor * KQ_masked = ggml_diag_mask_inf(ctx0, KQ_scaled, n_past);
// KQ = soft_max(KQ_masked)
struct ggml_tensor * KQ_soft_max = ggml_soft_max(ctx0, KQ_masked);
// V_trans = Vmem.view(n_embd/n_head, n_head, n_past + N).permute(1, 2, 0, 3).contiguous()
struct ggml_tensor * V_trans =
ggml_cpy(ctx0,
ggml_permute(ctx0,
ggml_reshape_3d(ctx0,
ggml_view_1d(ctx0, kv_self.v, (n_past + N)*n_embd, il*n_ctx*ggml_element_size(kv_self.v)*n_embd),
n_embd/n_head, n_head, n_past + N),
1, 2, 0, 3),
ggml_new_tensor_3d(ctx0, kv_self.v->type, n_past + N, n_embd/n_head, n_head));
// KQV = transpose(V) * KQ_soft_max
struct ggml_tensor * KQV = ggml_mul_mat(ctx0, V_trans, KQ_soft_max);
// KQV_merged = KQV.permute(0, 2, 1, 3)
struct ggml_tensor * KQV_merged = ggml_permute(ctx0, KQV, 0, 2, 1, 3);
// cur = KQV_merged.contiguous().view(n_embd, N)
cur = ggml_cpy(ctx0,
KQV_merged,
ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_embd, N));
// projection (no bias)
cur = ggml_mul_mat(ctx0,
model.layers[il].wo,
cur);
}
lctx.use_buf(ctx0, 1);
struct ggml_tensor * inpFF = ggml_add(ctx0, cur, inpSA);
// feed-forward network
{
// norm
{
cur = ggml_rms_norm(ctx0, inpFF);
// cur = ffn_norm*cur
cur = ggml_mul(ctx0,
ggml_repeat(ctx0, model.layers[il].ffn_norm, cur),
cur);
}
struct ggml_tensor * tmp = ggml_mul_mat(ctx0,
model.layers[il].w3,
cur);
cur = ggml_mul_mat(ctx0,
model.layers[il].w1,
cur);
// SILU activation
cur = ggml_silu(ctx0, cur);
cur = ggml_mul(ctx0, cur, tmp);
cur = ggml_mul_mat(ctx0,
model.layers[il].w2,
cur);
}
cur = ggml_add(ctx0, cur, inpFF);
// input for next layer
inpL = cur;
}
lctx.use_buf(ctx0, 0);
// used at the end to optionally extract the embeddings
struct ggml_tensor * embeddings = NULL;
// norm
{
inpL = ggml_rms_norm(ctx0, inpL);
// inpL = norm*inpL
inpL = ggml_mul(ctx0,
ggml_repeat(ctx0, model.norm, inpL),
inpL);
embeddings = inpL;
}
// lm_head
inpL = ggml_mul_mat(ctx0, model.output, inpL);
lctx.use_buf(ctx0, -1);
// logits -> probs
//inpL = ggml_soft_max(ctx0, inpL);
// run the computation
ggml_build_forward_expand(&gf, inpL);
ggml_graph_compute (ctx0, &gf);
//if (n_past%100 == 0) {
// ggml_graph_print (&gf);
// ggml_graph_dump_dot(&gf, NULL, "gpt-2.dot");
//}
//embd_w.resize(n_vocab*N);
//memcpy(embd_w.data(), ggml_get_data(inpL), sizeof(float)*n_vocab*N);
// extract logits
{
auto & logits_out = lctx.logits;
if (lctx.logits_all) {
logits_out.resize(n_vocab * N);
memcpy(logits_out.data(), (float *) ggml_get_data(inpL), sizeof(float)*n_vocab*N);
} else {
// return result for just the last token
logits_out.resize(n_vocab);
memcpy(logits_out.data(), (float *) ggml_get_data(inpL) + (n_vocab*(N-1)), sizeof(float)*n_vocab);
}
}
// extract embeddings
if (lctx.embedding.size()) {
auto & embedding_out = lctx.embedding;
embedding_out.resize(n_embd);
memcpy(embedding_out.data(), (float *) ggml_get_data(embeddings) + (n_embd*(N - 1)), sizeof(float)*n_embd);
}
if (mem_per_token == 0) {
mem_per_token = ggml_used_mem(ctx0)/N;
}
#if 0
printf("\n%s: used_mem = %.3f MB, scratch -- %.3f MB %.3f MB\n", __func__,
ggml_used_mem(ctx0)/1024.0/1024.0,
lctx.get_buf_max_mem(0)/1024.0/1024.0,
lctx.get_buf_max_mem(1)/1024.0/1024.0);
#endif
ggml_free(ctx0);