Skip to content
Navigation Menu
{{ message }}
forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy patharg.cpp
More file actions
3547 lines (3421 loc) · 156 KB
/
Copy patharg.cpp
File metadata and controls
3547 lines (3421 loc) · 156 KB
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 "arg.h"
#include "chat.h"
#include "common.h"
#include "json-schema-to-grammar.h"
#include "log.h"
#include "sampling.h"
#include "download.h"
// fix problem with std::min and std::max
#if defined(_WIN32)
#define WIN32_LEAN_AND_MEAN
#ifndef NOMINMAX
# define NOMINMAX
#endif
#include <windows.h>
#endif
#define JSON_ASSERT GGML_ASSERT
#include <nlohmann/json.hpp>
#include <algorithm>
#include <cinttypes>
#include <climits>
#include <cstdarg>
#include <fstream>
#include <list>
#include <regex>
#include <set>
#include <string>
#include <thread> // for hardware_concurrency
#include <vector>
#ifndef __EMSCRIPTEN__
#ifdef __linux__
#include <linux/limits.h>
#elif defined(_WIN32)
# if !defined(PATH_MAX)
# define PATH_MAX MAX_PATH
# endif
#elif defined(_AIX)
#include <sys/limits.h>
#else
#include <sys/syslimits.h>
#endif
#endif
#define LLAMA_MAX_URL_LENGTH 2084 // Maximum URL Length in Chrome: 2083
using json = nlohmann::ordered_json;
using namespace common_arg_utils;
static std::initializer_list<enum llama_example> mmproj_examples = {
LLAMA_EXAMPLE_MTMD,
LLAMA_EXAMPLE_SERVER,
LLAMA_EXAMPLE_CLI,
};
static std::string read_file(const std::string & fname) {
std::ifstream file(fname);
if (!file) {
throw std::runtime_error(string_format("error: failed to open file '%s'\n", fname.c_str()));
}
std::string content((std::istreambuf_iterator<char>(file)), std::istreambuf_iterator<char>());
file.close();
return content;
}
static const std::vector<common_arg> & get_common_arg_defs() {
static const std::vector<common_arg> options = [] {
common_params params;
auto ctx = common_params_parser_init(params, LLAMA_EXAMPLE_SERVER, nullptr);
return ctx.options;
}();
return options;
}
common_arg & common_arg::set_examples(std::initializer_list<enum llama_example> examples) {
this->examples = examples;
return *this;
}
common_arg & common_arg::set_excludes(std::initializer_list<enum llama_example> excludes) {
this->excludes = excludes;
return *this;
}
common_arg & common_arg::set_env(const char * env) {
help = help + "\n(env: " + env + ")";
this->env = env;
return *this;
}
common_arg & common_arg::set_sparam() {
is_sparam = true;
return *this;
}
common_arg & common_arg::set_preset_only() {
is_preset_only = true;
return *this;
}
bool common_arg::in_example(enum llama_example ex) {
return examples.find(ex) != examples.end();
}
bool common_arg::is_exclude(enum llama_example ex) {
return excludes.find(ex) != excludes.end();
}
bool common_arg::get_value_from_env(std::string & output) const {
if (env == nullptr) return false;
if (!args_neg.empty()) {
// for compatibility, we need to check LLAMA_ARG_NO_ env as well
std::string neg_env = env;
string_replace_all(neg_env, "LLAMA_ARG_", "LLAMA_ARG_NO_");
char * neg_value = std::getenv(neg_env.c_str());
if (neg_value) {
output = "0"; // falsey
return true;
}
}
char * value = std::getenv(env);
if (value) {
output = value;
return true;
}
return false;
}
bool common_arg::has_value_from_env() const {
if (env != nullptr && !args_neg.empty()) {
// for compatibility, we need to check LLAMA_ARG_NO_ env as well
std::string neg_env = env;
string_replace_all(neg_env, "LLAMA_ARG_", "LLAMA_ARG_NO_");
if (std::getenv(neg_env.c_str())) {
return true;
}
}
return env != nullptr && std::getenv(env);
}
static std::vector<std::string> break_str_into_lines(std::string input, size_t max_char_per_line) {
std::vector<std::string> result;
std::istringstream iss(input);
std::string line;
auto add_line = [&](const std::string& l) {
if (l.length() <= max_char_per_line) {
result.push_back(l);
} else {
std::istringstream line_stream(l);
std::string word, current_line;
while (line_stream >> word) {
if (current_line.length() + !current_line.empty() + word.length() > max_char_per_line) {
if (!current_line.empty()) result.push_back(current_line);
current_line = word;
} else {
current_line += (!current_line.empty() ? " " : "") + word;
}
}
if (!current_line.empty()) result.push_back(current_line);
}
};
while (std::getline(iss, line)) {
add_line(line);
}
return result;
}
std::string common_arg::to_string() const {
// params for printing to console
const static int n_leading_spaces = 40;
const static int n_char_per_line_help = 70; // TODO: detect this based on current console
std::string leading_spaces(n_leading_spaces, ' ');
std::ostringstream ss;
auto all_args = get_args(); // also contains args_neg
for (const auto & arg : all_args) {
if (arg == all_args.front()) {
if (all_args.size() == 1) {
ss << arg;
} else {
// first arg is usually abbreviation, we need padding to make it more beautiful
auto tmp = std::string(arg) + ", ";
auto spaces = std::string(std::max(0, 7 - (int)tmp.size()), ' ');
ss << tmp << spaces;
}
} else {
ss << arg << (arg != all_args.back() ? ", " : "");
}
}
if (value_hint) ss << " " << value_hint;
if (value_hint_2) ss << " " << value_hint_2;
if (ss.tellp() > n_leading_spaces - 3) {
// current line is too long, add new line
ss << "\n" << leading_spaces;
} else {
// padding between arg and help, same line
ss << std::string(leading_spaces.size() - ss.tellp(), ' ');
}
const auto help_lines = break_str_into_lines(help, n_char_per_line_help);
for (const auto & line : help_lines) {
ss << (&line == &help_lines.front() ? "" : leading_spaces) << line << "\n";
}
return ss.str();
}
std::vector<std::string> common_arg::get_args() const {
std::vector<std::string> result;
for (const auto & arg : args) {
result.push_back(std::string(arg));
}
for (const auto & arg : args_neg) {
result.push_back(std::string(arg));
}
return result;
}
std::vector<std::string> common_arg::get_env() const {
std::vector<std::string> result;
if (env) {
result.push_back(std::string(env));
}
if (!args_neg.empty() && env) {
// for compatibility, we need to add LLAMA_ARG_NO_ variant
std::string neg_env = env;
string_replace_all(neg_env, "LLAMA_ARG_", "LLAMA_ARG_NO_");
result.push_back(neg_env);
}
return result;
}
//
// utils
//
// Helper function to parse tensor buffer override strings
static void parse_tensor_buffer_overrides(const std::string & value, std::vector<llama_model_tensor_buft_override> & overrides) {
std::map<std::string, ggml_backend_buffer_type_t> buft_list;
for (size_t i = 0; i < ggml_backend_dev_count(); ++i) {
auto * dev = ggml_backend_dev_get(i);
auto * buft = ggml_backend_dev_buffer_type(dev);
if (buft) {
buft_list[ggml_backend_buft_name(buft)] = buft;
}
}
for (const auto & override : string_split<std::string>(value, ',')) {
std::string::size_type pos = override.find('=');
if (pos == std::string::npos) {
throw std::invalid_argument("invalid value");
}
std::string tensor_name = override.substr(0, pos);
std::string buffer_type = override.substr(pos + 1);
if (buft_list.find(buffer_type) == buft_list.end()) {
printf("Available buffer types:\n");
for (const auto & it : buft_list) {
printf(" %s\n", ggml_backend_buft_name(it.second));
}
throw std::invalid_argument("unknown buffer type");
}
// keep strings alive and avoid leaking memory by storing them in a static vector
static std::list<std::string> buft_overrides;
buft_overrides.push_back(tensor_name);
overrides.push_back({buft_overrides.back().c_str(), buft_list.at(buffer_type)});
}
}
struct handle_model_result {
bool found_mmproj = false;
common_params_model mmproj;
};
static handle_model_result common_params_handle_model(
struct common_params_model & model,
const std::string & bearer_token,
bool offline) {
handle_model_result result;
// handle pre-fill default model path and url based on hf_repo and hf_file
{
if (!model.docker_repo.empty()) { // Handle Docker URLs by resolving them to local paths
model.path = common_docker_resolve_model(model.docker_repo);
model.name = model.docker_repo; // set name for consistency
} else if (!model.hf_repo.empty()) {
// short-hand to avoid specifying --hf-file -> default it to --model
if (model.hf_file.empty()) {
if (model.path.empty()) {
auto auto_detected = common_get_hf_file(model.hf_repo, bearer_token, offline);
if (auto_detected.repo.empty() || auto_detected.ggufFile.empty()) {
exit(1); // built without CURL, error message already printed
}
model.name = model.hf_repo; // repo name with tag
model.hf_repo = auto_detected.repo; // repo name without tag
model.hf_file = auto_detected.ggufFile;
if (!auto_detected.mmprojFile.empty()) {
result.found_mmproj = true;
result.mmproj.hf_repo = model.hf_repo;
result.mmproj.hf_file = auto_detected.mmprojFile;
}
} else {
model.hf_file = model.path;
}
}
std::string model_endpoint = get_model_endpoint();
model.url = model_endpoint + model.hf_repo + "/resolve/main/" + model.hf_file;
// make sure model path is present (for caching purposes)
if (model.path.empty()) {
// this is to avoid different repo having same file name, or same file name in different subdirs
std::string filename = model.hf_repo + "_" + model.hf_file;
// to make sure we don't have any slashes in the filename
string_replace_all(filename, "/", "_");
model.path = fs_get_cache_file(filename);
}
} else if (!model.url.empty()) {
if (model.path.empty()) {
auto f = string_split<std::string>(model.url, '#').front();
f = string_split<std::string>(f, '?').front();
model.path = fs_get_cache_file(string_split<std::string>(f, '/').back());
}
}
}
// then, download it if needed
if (!model.url.empty()) {
bool ok = common_download_model(model, bearer_token, offline);
if (!ok) {
LOG_ERR("error: failed to download model from %s\n", model.url.c_str());
exit(1);
}
}
return result;
}
const std::vector<ggml_type> kv_cache_types = {
GGML_TYPE_F32,
GGML_TYPE_F16,
GGML_TYPE_BF16,
GGML_TYPE_Q8_0,
GGML_TYPE_Q4_0,
GGML_TYPE_Q4_1,
GGML_TYPE_IQ4_NL,
GGML_TYPE_Q5_0,
GGML_TYPE_Q5_1,
};
static ggml_type kv_cache_type_from_str(const std::string & s) {
for (const auto & type : kv_cache_types) {
if (ggml_type_name(type) == s) {
return type;
}
}
throw std::runtime_error("Unsupported cache type: " + s);
}
static std::string get_all_kv_cache_types() {
std::ostringstream msg;
for (const auto & type : kv_cache_types) {
msg << ggml_type_name(type) << (&type == &kv_cache_types.back() ? "" : ", ");
}
return msg.str();
}
static bool parse_bool_value(const std::string & value) {
if (is_truthy(value)) {
return true;
} else if (is_falsey(value)) {
return false;
} else {
throw std::invalid_argument("invalid boolean value");
}
}
//
// CLI argument parsing functions
//
static bool common_params_parse_ex(int argc, char ** argv, common_params_context & ctx_arg) {
common_params & params = ctx_arg.params;
std::unordered_map<std::string, std::pair<common_arg *, bool>> arg_to_options;
for (auto & opt : ctx_arg.options) {
for (const auto & arg : opt.args) {
arg_to_options[arg] = {&opt, /* is_positive */ true};
}
for (const auto & arg : opt.args_neg) {
arg_to_options[arg] = {&opt, /* is_positive */ false};
}
}
// handle environment variables
for (auto & opt : ctx_arg.options) {
std::string value;
if (opt.get_value_from_env(value)) {
try {
if (opt.handler_void && is_truthy(value)) {
opt.handler_void(params);
}
if (opt.handler_int) {
opt.handler_int(params, std::stoi(value));
}
if (opt.handler_bool) {
opt.handler_bool(params, parse_bool_value(value));
}
if (opt.handler_string) {
opt.handler_string(params, value);
continue;
}
} catch (std::exception & e) {
throw std::invalid_argument(string_format(
"error while handling environment variable \"%s\": %s\n\n", opt.env, e.what()));
}
}
}
// handle command line arguments
auto check_arg = [&](int i) {
if (i+1 >= argc) {
throw std::invalid_argument("expected value for argument");
}
};
std::set<std::string> seen_args;
for (int i = 1; i < argc; i++) {
const std::string arg_prefix = "--";
std::string arg = argv[i];
if (arg.compare(0, arg_prefix.size(), arg_prefix) == 0) {
std::replace(arg.begin(), arg.end(), '_', '-');
}
if (arg_to_options.find(arg) == arg_to_options.end()) {
throw std::invalid_argument(string_format("error: invalid argument: %s", arg.c_str()));
}
if (!seen_args.insert(arg).second) {
LOG_WRN("DEPRECATED: argument '%s' specified multiple times, use comma-separated values instead (only last value will be used)\n", arg.c_str());
}
auto & tmp = arg_to_options[arg];
auto opt = *tmp.first;
bool is_positive = tmp.second;
if (opt.has_value_from_env()) {
fprintf(stderr, "warn: %s environment variable is set, but will be overwritten by command line argument %s\n", opt.env, arg.c_str());
}
try {
if (opt.handler_void) {
opt.handler_void(params);
continue;
}
if (opt.handler_bool) {
opt.handler_bool(params, is_positive);
continue;
}
// arg with single value
check_arg(i);
std::string val = argv[++i];
if (opt.handler_int) {
opt.handler_int(params, std::stoi(val));
continue;
}
if (opt.handler_string) {
opt.handler_string(params, val);
continue;
}
// arg with 2 values
check_arg(i);
std::string val2 = argv[++i];
if (opt.handler_str_str) {
opt.handler_str_str(params, val, val2);
continue;
}
} catch (std::exception & e) {
throw std::invalid_argument(string_format(
"error while handling argument \"%s\": %s\n\n"
"usage:\n%s\n\nto show complete usage, run with -h",
arg.c_str(), e.what(), opt.to_string().c_str()));
}
}
postprocess_cpu_params(params.cpuparams, nullptr);
postprocess_cpu_params(params.cpuparams_batch, ¶ms.cpuparams);
postprocess_cpu_params(params.speculative.cpuparams, ¶ms.cpuparams);
postprocess_cpu_params(params.speculative.cpuparams_batch, ¶ms.cpuparams_batch);
if (params.prompt_cache_all && (params.interactive || params.interactive_first)) {
throw std::invalid_argument("error: --prompt-cache-all not supported in interactive mode yet\n");
}
// handle model and download
{
auto res = common_params_handle_model(params.model, params.hf_token, params.offline);
if (params.no_mmproj) {
params.mmproj = {};
} else if (res.found_mmproj && params.mmproj.path.empty() && params.mmproj.url.empty()) {
// optionally, handle mmproj model when -hf is specified
params.mmproj = res.mmproj;
}
// only download mmproj if the current example is using it
for (auto & ex : mmproj_examples) {
if (ctx_arg.ex == ex) {
common_params_handle_model(params.mmproj, params.hf_token, params.offline);
break;
}
}
common_params_handle_model(params.speculative.model, params.hf_token, params.offline);
common_params_handle_model(params.vocoder.model, params.hf_token, params.offline);
}
// model is required (except for server)
// TODO @ngxson : maybe show a list of available models in CLI in this case
if (params.model.path.empty() && ctx_arg.ex != LLAMA_EXAMPLE_SERVER && !params.usage && !params.completion) {
throw std::invalid_argument("error: --model is required\n");
}
if (params.escape) {
string_process_escapes(params.prompt);
string_process_escapes(params.input_prefix);
string_process_escapes(params.input_suffix);
for (auto & antiprompt : params.antiprompt) {
string_process_escapes(antiprompt);
}
for (auto & seq_breaker : params.sampling.dry_sequence_breakers) {
string_process_escapes(seq_breaker);
}
for (auto & pair : params.speculative.replacements) {
string_process_escapes(pair.first);
string_process_escapes(pair.second);
}
}
if (!params.kv_overrides.empty()) {
params.kv_overrides.emplace_back();
params.kv_overrides.back().key[0] = 0;
}
// pad tensor_buft_overrides for llama_params_fit:
const size_t ntbo = llama_max_tensor_buft_overrides();
while (params.tensor_buft_overrides.size() < ntbo) {
params.tensor_buft_overrides.push_back({nullptr, nullptr});
}
if (!params.speculative.tensor_buft_overrides.empty()) {
params.speculative.tensor_buft_overrides.push_back({nullptr, nullptr});
}
if (!params.chat_template.empty() && !common_chat_verify_template(params.chat_template, params.use_jinja)) {
throw std::runtime_error(string_format(
"error: the supplied chat template is not supported: %s%s\n",
params.chat_template.c_str(),
params.use_jinja ? "" : "\nnote: llama.cpp was started without --jinja, we only support commonly used templates"
));
}
common_log_set_verbosity_thold(params.verbosity);
return true;
}
static void common_params_print_usage(common_params_context & ctx_arg) {
auto print_options = [](std::vector<common_arg *> & options) {
for (common_arg * opt : options) {
printf("%s", opt->to_string().c_str());
}
};
std::vector<common_arg *> common_options;
std::vector<common_arg *> sparam_options;
std::vector<common_arg *> specific_options;
for (auto & opt : ctx_arg.options) {
// in case multiple LLAMA_EXAMPLE_* are set, we prioritize the LLAMA_EXAMPLE_* matching current example
if (opt.is_sparam) {
sparam_options.push_back(&opt);
} else if (opt.in_example(ctx_arg.ex)) {
specific_options.push_back(&opt);
} else {
common_options.push_back(&opt);
}
}
printf("----- common params -----\n\n");
print_options(common_options);
printf("\n\n----- sampling params -----\n\n");
print_options(sparam_options);
// TODO: maybe convert enum llama_example to string
printf("\n\n----- example-specific params -----\n\n");
print_options(specific_options);
}
static void common_params_print_completion(common_params_context & ctx_arg) {
std::vector<common_arg *> common_options;
std::vector<common_arg *> sparam_options;
std::vector<common_arg *> specific_options;
for (auto & opt : ctx_arg.options) {
if (opt.is_sparam) {
sparam_options.push_back(&opt);
} else if (opt.in_example(ctx_arg.ex)) {
specific_options.push_back(&opt);
} else {
common_options.push_back(&opt);
}
}
printf("_llama_completions() {\n");
printf(" local cur prev opts\n");
printf(" COMPREPLY=()\n");
printf(" cur=\"${COMP_WORDS[COMP_CWORD]}\"\n");
printf(" prev=\"${COMP_WORDS[COMP_CWORD-1]}\"\n\n");
printf(" opts=\"");
auto print_options = [](const std::vector<common_arg *> & options) {
for (const common_arg * opt : options) {
for (const char * arg : opt->args) {
printf("%s ", arg);
}
}
};
print_options(common_options);
print_options(sparam_options);
print_options(specific_options);
printf("\"\n\n");
printf(" case \"$prev\" in\n");
printf(" --model|-m)\n");
printf(" COMPREPLY=( $(compgen -f -X '!*.gguf' -- \"$cur\") $(compgen -d -- \"$cur\") )\n");
printf(" return 0\n");
printf(" ;;\n");
printf(" --grammar-file)\n");
printf(" COMPREPLY=( $(compgen -f -X '!*.gbnf' -- \"$cur\") $(compgen -d -- \"$cur\") )\n");
printf(" return 0\n");
printf(" ;;\n");
printf(" --chat-template-file)\n");
printf(" COMPREPLY=( $(compgen -f -X '!*.jinja' -- \"$cur\") $(compgen -d -- \"$cur\") )\n");
printf(" return 0\n");
printf(" ;;\n");
printf(" *)\n");
printf(" COMPREPLY=( $(compgen -W \"${opts}\" -- \"$cur\") )\n");
printf(" return 0\n");
printf(" ;;\n");
printf(" esac\n");
printf("}\n\n");
std::set<std::string> executables = {
"llama-batched",
"llama-batched-bench",
"llama-bench",
"llama-cli",
"llama-completion",
"llama-convert-llama2c-to-ggml",
"llama-cvector-generator",
"llama-embedding",
"llama-eval-callback",
"llama-export-lora",
"llama-gen-docs",
"llama-gguf",
"llama-gguf-hash",
"llama-gguf-split",
"llama-gritlm",
"llama-imatrix",
"llama-infill",
"llama-mtmd-cli",
"llama-llava-clip-quantize-cli",
"llama-lookahead",
"llama-lookup",
"llama-lookup-create",
"llama-lookup-merge",
"llama-lookup-stats",
"llama-parallel",
"llama-passkey",
"llama-perplexity",
"llama-q8dot",
"llama-quantize",
"llama-qwen2vl-cli",
"llama-retrieval",
"llama-run",
"llama-save-load-state",
"llama-server",
"llama-simple",
"llama-simple-chat",
"llama-speculative",
"llama-speculative-simple",
"llama-tokenize",
"llama-tts",
"llama-vdot"
};
for (const auto& exe : executables) {
printf("complete -F _llama_completions %s\n", exe.c_str());
}
}
static std::vector<ggml_backend_dev_t> parse_device_list(const std::string & value) {
std::vector<ggml_backend_dev_t> devices;
auto dev_names = string_split<std::string>(value, ',');
if (dev_names.empty()) {
throw std::invalid_argument("no devices specified");
}
if (dev_names.size() == 1 && dev_names[0] == "none") {
devices.push_back(nullptr);
} else {
for (const auto & device : dev_names) {
auto * dev = ggml_backend_dev_by_name(device.c_str());
if (!dev || ggml_backend_dev_type(dev) == GGML_BACKEND_DEVICE_TYPE_CPU) {
throw std::invalid_argument(string_format("invalid device: %s", device.c_str()));
}
devices.push_back(dev);
}
devices.push_back(nullptr);
}
return devices;
}
static void add_rpc_devices(const std::string & servers) {
auto rpc_servers = string_split<std::string>(servers, ',');
if (rpc_servers.empty()) {
throw std::invalid_argument("no RPC servers specified");
}
ggml_backend_reg_t rpc_reg = ggml_backend_reg_by_name("RPC");
if (!rpc_reg) {
throw std::invalid_argument("failed to find RPC backend");
}
typedef ggml_backend_reg_t (*ggml_backend_rpc_add_server_t)(const char * endpoint);
ggml_backend_rpc_add_server_t ggml_backend_rpc_add_server_fn = (ggml_backend_rpc_add_server_t) ggml_backend_reg_get_proc_address(rpc_reg, "ggml_backend_rpc_add_server");
if (!ggml_backend_rpc_add_server_fn) {
throw std::invalid_argument("failed to find RPC add server function");
}
for (const auto & server : rpc_servers) {
auto reg = ggml_backend_rpc_add_server_fn(server.c_str());
ggml_backend_register(reg);
}
}
bool common_params_to_map(int argc, char ** argv, llama_example ex, std::map<common_arg, std::string> & out_map) {
common_params dummy_params;
common_params_context ctx_arg = common_params_parser_init(dummy_params, ex, nullptr);
std::unordered_map<std::string, common_arg *> arg_to_options;
for (auto & opt : ctx_arg.options) {
for (const auto & arg : opt.args) {
arg_to_options[arg] = &opt;
}
for (const auto & arg : opt.args_neg) {
arg_to_options[arg] = &opt;
}
}
// TODO @ngxson : find a way to deduplicate this code
// handle command line arguments
auto check_arg = [&](int i) {
if (i+1 >= argc) {
throw std::invalid_argument("expected value for argument");
}
};
std::set<std::string> seen_args;
for (int i = 1; i < argc; i++) {
const std::string arg_prefix = "--";
std::string arg = argv[i];
if (arg.compare(0, arg_prefix.size(), arg_prefix) == 0) {
std::replace(arg.begin(), arg.end(), '_', '-');
}
if (arg_to_options.find(arg) == arg_to_options.end()) {
throw std::invalid_argument(string_format("error: invalid argument: %s", arg.c_str()));
}
if (!seen_args.insert(arg).second) {
LOG_WRN("DEPRECATED: argument '%s' specified multiple times, use comma-separated values instead (only last value will be used)\n", arg.c_str());
}
auto opt = *arg_to_options[arg];
std::string val;
if (opt.value_hint == nullptr && opt.value_hint_2 == nullptr) {
// bool arg (need to reverse the meaning for negative args)
bool is_neg = std::find(opt.args_neg.begin(), opt.args_neg.end(), arg) != opt.args_neg.end();
val = is_neg ? "0" : "1";
}
if (opt.value_hint != nullptr) {
// arg with single value
check_arg(i);
val = argv[++i];
}
if (opt.value_hint_2 != nullptr) {
// TODO: support arg with 2 values
throw std::invalid_argument("error: argument with 2 values is not yet supported\n");
}
out_map[opt] = val;
}
return true;
}
bool common_params_parse(int argc, char ** argv, common_params & params, llama_example ex, void(*print_usage)(int, char **)) {
auto ctx_arg = common_params_parser_init(params, ex, print_usage);
const common_params params_org = ctx_arg.params; // the example can modify the default params
try {
if (!common_params_parse_ex(argc, argv, ctx_arg)) {
ctx_arg.params = params_org;
return false;
}
if (ctx_arg.params.usage) {
common_params_print_usage(ctx_arg);
if (ctx_arg.print_usage) {
ctx_arg.print_usage(argc, argv);
}
exit(0);
}
if (ctx_arg.params.completion) {
common_params_print_completion(ctx_arg);
exit(0);
}
params.lr.init();
} catch (const std::invalid_argument & ex) {
fprintf(stderr, "%s\n", ex.what());
ctx_arg.params = params_org;
return false;
} catch (std::exception & ex) {
fprintf(stderr, "%s\n", ex.what());
exit(1); // for other exceptions, we exit with status code 1
}
return true;
}
static std::string list_builtin_chat_templates() {
std::vector<const char *> supported_tmpl;
int32_t res = llama_chat_builtin_templates(nullptr, 0);
supported_tmpl.resize(res);
res = llama_chat_builtin_templates(supported_tmpl.data(), supported_tmpl.size());
std::ostringstream msg;
for (auto & tmpl : supported_tmpl) {
msg << tmpl << (&tmpl == &supported_tmpl.back() ? "" : ", ");
}
return msg.str();
}
bool common_arg_utils::is_truthy(const std::string & value) {
return value == "on" || value == "enabled" || value == "true" || value == "1";
}
bool common_arg_utils::is_falsey(const std::string & value) {
return value == "off" || value == "disabled" || value == "false" || value == "0";
}
bool common_arg_utils::is_autoy(const std::string & value) {
return value == "auto" || value == "-1";
}
common_params_context common_params_parser_init(common_params & params, llama_example ex, void(*print_usage)(int, char **)) {
// per-example default params
// we define here to make sure it's included in llama-gen-docs
if (ex == LLAMA_EXAMPLE_COMPLETION) {
params.use_jinja = false; // disable jinja by default
} else if (ex == LLAMA_EXAMPLE_MTMD) {
params.use_jinja = false; // disable jinja by default
params.sampling.temp = 0.2; // lower temp by default for better quality
} else if (ex == LLAMA_EXAMPLE_SERVER) {
params.n_parallel = -1; // auto by default
}
params.use_color = tty_can_use_colors();
// load dynamic backends
ggml_backend_load_all();
common_params_context ctx_arg(params);
ctx_arg.print_usage = print_usage;
ctx_arg.ex = ex;
std::string sampler_type_chars;
std::string sampler_type_names;
for (const auto & sampler : params.sampling.samplers) {
sampler_type_chars += common_sampler_type_to_chr(sampler);
sampler_type_names += common_sampler_type_to_str(sampler) + ";";
}
if (!sampler_type_names.empty()) {
sampler_type_names.pop_back(); // remove last semicolon
}
/**
* filter options by example
* rules:
* - all examples inherit options from LLAMA_EXAMPLE_COMMON
* - if LLAMA_EXAMPLE_* is set (other than COMMON), we only show the option in the corresponding example
* - if both {LLAMA_EXAMPLE_COMMON, LLAMA_EXAMPLE_*,} are set, we will prioritize the LLAMA_EXAMPLE_* matching current example
*/
auto add_opt = [&](common_arg arg) {
if ((arg.in_example(ex) || arg.in_example(LLAMA_EXAMPLE_COMMON)) && !arg.is_exclude(ex)) {
ctx_arg.options.push_back(std::move(arg));
}
};
add_opt(common_arg(
{"-h", "--help", "--usage"},
"print usage and exit",
[](common_params & params) {
params.usage = true;
}
));
add_opt(common_arg(
{"--version"},
"show version and build info",
[](common_params &) {
fprintf(stderr, "version: %d (%s)\n", LLAMA_BUILD_NUMBER, LLAMA_COMMIT);
fprintf(stderr, "built with %s for %s\n", LLAMA_COMPILER, LLAMA_BUILD_TARGET);
exit(0);
}
));
add_opt(common_arg(
{"-cl", "--cache-list"},
"show list of models in cache",
[](common_params &) {
printf("model cache directory: %s\n", fs_get_cache_directory().c_str());
auto models = common_list_cached_models();
printf("number of models in cache: %zu\n", models.size());
for (size_t i = 0; i < models.size(); i++) {
auto & model = models[i];
printf("%4d. %s\n", (int) i + 1, model.to_string().c_str());
}
exit(0);
}
));
add_opt(common_arg(
{"--completion-bash"},
"print source-able bash completion script for llama.cpp",
[](common_params & params) {
params.completion = true;
}
));
add_opt(common_arg(
{"--verbose-prompt"},
string_format("print a verbose prompt before generation (default: %s)", params.verbose_prompt ? "true" : "false"),
[](common_params & params) {
params.verbose_prompt = true;
}
));
add_opt(common_arg(
{"--display-prompt"},
{"--no-display-prompt"},
string_format("whether to print prompt at generation (default: %s)", params.display_prompt ? "true" : "false"),
[](common_params & params, bool value) {
params.display_prompt = value;
}
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"-co", "--color"}, "[on|off|auto]",
"Colorize output to distinguish prompt and user input from generations ('on', 'off', or 'auto', default: 'auto')\n"
"'auto' enables colors when output is to a terminal",
[](common_params & params, const std::string & value) {
if (is_truthy(value)) {
params.use_color = true;
} else if (is_falsey(value)) {
params.use_color = false;
} else if (is_autoy(value)) {
params.use_color = tty_can_use_colors();
} else {
throw std::invalid_argument(
string_format("error: unknown value for --color: '%s'\n", value.c_str()));
}
}
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_LOOKUP}));
add_opt(common_arg(
{"-t", "--threads"}, "N",
string_format("number of CPU threads to use during generation (default: %d)", params.cpuparams.n_threads),
[](common_params & params, int value) {
params.cpuparams.n_threads = value;
if (params.cpuparams.n_threads <= 0) {
params.cpuparams.n_threads = std::thread::hardware_concurrency();
}
}
).set_env("LLAMA_ARG_THREADS"));
add_opt(common_arg(
{"-tb", "--threads-batch"}, "N",
"number of threads to use during batch and prompt processing (default: same as --threads)",
[](common_params & params, int value) {
params.cpuparams_batch.n_threads = value;
if (params.cpuparams_batch.n_threads <= 0) {
params.cpuparams_batch.n_threads = std::thread::hardware_concurrency();
}
}
));
add_opt(common_arg(
{"-C", "--cpu-mask"}, "M",
"CPU affinity mask: arbitrarily long hex. Complements cpu-range (default: \"\")",
[](common_params & params, const std::string & mask) {
params.cpuparams.mask_valid = true;
if (!parse_cpu_mask(mask, params.cpuparams.cpumask)) {
throw std::invalid_argument("invalid cpumask");
You can’t perform that action at this time.