summaryrefslogtreecommitdiff
path: root/examples
diff options
context:
space:
mode:
Diffstat (limited to 'examples')
-rw-r--r--examples/batched/batched.cpp2
-rw-r--r--examples/embedding/embedding.cpp4
-rw-r--r--examples/eval-callback/eval-callback.cpp4
-rw-r--r--examples/imatrix/imatrix.cpp4
-rw-r--r--examples/infill/infill.cpp16
-rw-r--r--examples/llama-bench/llama-bench.cpp2
-rw-r--r--examples/llava/llava-cli.cpp2
-rw-r--r--examples/lookahead/lookahead.cpp2
-rw-r--r--examples/lookup/lookup.cpp2
-rw-r--r--examples/main/main.cpp16
-rw-r--r--examples/parallel/parallel.cpp2
-rw-r--r--examples/perplexity/perplexity.cpp14
-rw-r--r--examples/quantize/quantize.cpp2
-rw-r--r--examples/retrieval/retrieval.cpp4
-rw-r--r--examples/server/server.cpp10
15 files changed, 43 insertions, 43 deletions
diff --git a/examples/batched/batched.cpp b/examples/batched/batched.cpp
index be30d20b..591bc6e5 100644
--- a/examples/batched/batched.cpp
+++ b/examples/batched/batched.cpp
@@ -48,7 +48,7 @@ int main(int argc, char ** argv) {
params.prompt = "Hello my name is";
}
- process_escapes(params.prompt);
+ string_process_escapes(params.prompt);
// init LLM
diff --git a/examples/embedding/embedding.cpp b/examples/embedding/embedding.cpp
index 0c921ed6..004399b5 100644
--- a/examples/embedding/embedding.cpp
+++ b/examples/embedding/embedding.cpp
@@ -80,7 +80,7 @@ int main(int argc, char ** argv) {
std::mt19937 rng(params.seed);
if (params.random_prompt) {
- params.prompt = gpt_random_prompt(rng);
+ params.prompt = string_random_prompt(rng);
}
llama_backend_init();
@@ -107,7 +107,7 @@ int main(int argc, char ** argv) {
// print system information
{
fprintf(stderr, "\n");
- fprintf(stderr, "%s\n", get_system_info(params).c_str());
+ fprintf(stderr, "%s\n", gpt_params_get_system_info(params).c_str());
}
// split the prompt into lines
diff --git a/examples/eval-callback/eval-callback.cpp b/examples/eval-callback/eval-callback.cpp
index e670d376..51d67d6d 100644
--- a/examples/eval-callback/eval-callback.cpp
+++ b/examples/eval-callback/eval-callback.cpp
@@ -152,7 +152,7 @@ int main(int argc, char ** argv) {
std::mt19937 rng(params.seed);
if (params.random_prompt) {
- params.prompt = gpt_random_prompt(rng);
+ params.prompt = string_random_prompt(rng);
}
llama_backend_init();
@@ -176,7 +176,7 @@ int main(int argc, char ** argv) {
// print system information
{
fprintf(stderr, "\n");
- fprintf(stderr, "%s\n", get_system_info(params).c_str());
+ fprintf(stderr, "%s\n", gpt_params_get_system_info(params).c_str());
}
bool OK = run(ctx, params);
diff --git a/examples/imatrix/imatrix.cpp b/examples/imatrix/imatrix.cpp
index 82b19fc4..25a2351c 100644
--- a/examples/imatrix/imatrix.cpp
+++ b/examples/imatrix/imatrix.cpp
@@ -598,7 +598,7 @@ int main(int argc, char ** argv) {
std::mt19937 rng(params.seed);
if (params.random_prompt) {
- params.prompt = gpt_random_prompt(rng);
+ params.prompt = string_random_prompt(rng);
}
sparams.dataset = params.prompt_file;
@@ -667,7 +667,7 @@ int main(int argc, char ** argv) {
// print system information
{
fprintf(stderr, "\n");
- fprintf(stderr, "%s\n", get_system_info(params).c_str());
+ fprintf(stderr, "%s\n", gpt_params_get_system_info(params).c_str());
}
bool OK = compute_imatrix(ctx, params, compute_ppl, from_chunk);
diff --git a/examples/infill/infill.cpp b/examples/infill/infill.cpp
index afac145f..539f7818 100644
--- a/examples/infill/infill.cpp
+++ b/examples/infill/infill.cpp
@@ -50,9 +50,9 @@ static void write_logfile(
return;
}
- const std::string timestamp = get_sortable_timestamp();
+ const std::string timestamp = string_get_sortable_timestamp();
- const bool success = create_directory_with_parents(params.logdir);
+ const bool success = fs_create_directory_with_parents(params.logdir);
if (!success) {
fprintf(stderr, "%s: warning: failed to create logdir %s, cannot write logfile\n",
__func__, params.logdir.c_str());
@@ -70,7 +70,7 @@ static void write_logfile(
fprintf(logfile, "binary: infill\n");
char model_desc[128];
llama_model_desc(model, model_desc, sizeof(model_desc));
- dump_non_result_info_yaml(logfile, params, ctx, timestamp, input_tokens, model_desc);
+ yaml_dump_non_result_info(logfile, params, ctx, timestamp, input_tokens, model_desc);
fprintf(logfile, "\n");
fprintf(logfile, "######################\n");
@@ -78,8 +78,8 @@ static void write_logfile(
fprintf(logfile, "######################\n");
fprintf(logfile, "\n");
- dump_string_yaml_multiline(logfile, "output", output.c_str());
- dump_vector_int_yaml(logfile, "output_tokens", output_tokens);
+ yaml_dump_string_multiline(logfile, "output", output.c_str());
+ yaml_dump_vector_int(logfile, "output_tokens", output_tokens);
llama_dump_timing_info_yaml(logfile, ctx);
fclose(logfile);
@@ -236,7 +236,7 @@ int main(int argc, char ** argv) {
// print system information
{
LOG_TEE("\n");
- LOG_TEE("%s\n", get_system_info(params).c_str());
+ LOG_TEE("%s\n", gpt_params_get_system_info(params).c_str());
}
const bool add_bos = llama_should_add_bos_token(model);
GGML_ASSERT(llama_add_eos_token(model) != 1);
@@ -621,8 +621,8 @@ int main(int argc, char ** argv) {
if (params.escape) {
//process escape sequences, for the initial prompt this is done in common.cpp when we load the params, but for the interactive mode we need to do it here
- process_escapes(params.input_prefix);
- process_escapes(params.input_suffix);
+ string_process_escapes(params.input_prefix);
+ string_process_escapes(params.input_suffix);
}
suff_rm_leading_spc = params.escape;
if (suff_rm_leading_spc && params.input_suffix.find_first_of(' ') == 0 && params.input_suffix.size() > 1) {
diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp
index 6bb1f70c..2afdb3ab 100644
--- a/examples/llama-bench/llama-bench.cpp
+++ b/examples/llama-bench/llama-bench.cpp
@@ -200,7 +200,7 @@ static const cmd_params cmd_params_defaults = {
/* n_ubatch */ {512},
/* type_k */ {GGML_TYPE_F16},
/* type_v */ {GGML_TYPE_F16},
- /* n_threads */ {get_math_cpu_count()},
+ /* n_threads */ {cpu_get_num_math()},
/* n_gpu_layers */ {99},
/* split_mode */ {LLAMA_SPLIT_MODE_LAYER},
/* main_gpu */ {0},
diff --git a/examples/llava/llava-cli.cpp b/examples/llava/llava-cli.cpp
index a6d67e5d..c974900f 100644
--- a/examples/llava/llava-cli.cpp
+++ b/examples/llava/llava-cli.cpp
@@ -290,7 +290,7 @@ int main(int argc, char ** argv) {
#endif // LOG_DISABLE_LOGS
if (params.mmproj.empty() || (params.image.empty() && !prompt_contains_image(params.prompt))) {
- gpt_print_usage(argc, argv, params);
+ gpt_params_print_usage(argc, argv, params);
show_additional_info(argc, argv);
return 1;
}
diff --git a/examples/lookahead/lookahead.cpp b/examples/lookahead/lookahead.cpp
index 9c3540b2..54f060a8 100644
--- a/examples/lookahead/lookahead.cpp
+++ b/examples/lookahead/lookahead.cpp
@@ -174,7 +174,7 @@ int main(int argc, char ** argv) {
// debug
if (dump_kv_cache) {
llama_kv_cache_view_update(ctx, &kvc_view);
- dump_kv_cache_view_seqs(kvc_view, 40);
+ llama_kv_cache_dump_view_seqs(kvc_view, 40);
}
// build the mask from https://lmsys.org/blog/2023-11-21-lookahead-decoding/
diff --git a/examples/lookup/lookup.cpp b/examples/lookup/lookup.cpp
index eebbd00a..83dbee91 100644
--- a/examples/lookup/lookup.cpp
+++ b/examples/lookup/lookup.cpp
@@ -121,7 +121,7 @@ int main(int argc, char ** argv){
// debug
if (dump_kv_cache) {
llama_kv_cache_view_update(ctx, &kvc_view);
- dump_kv_cache_view_seqs(kvc_view, 40);
+ llama_kv_cache_dump_view_seqs(kvc_view, 40);
}
// print current draft sequence
diff --git a/examples/main/main.cpp b/examples/main/main.cpp
index 832b51ee..791dc61a 100644
--- a/examples/main/main.cpp
+++ b/examples/main/main.cpp
@@ -60,9 +60,9 @@ static void write_logfile(
return;
}
- const std::string timestamp = get_sortable_timestamp();
+ const std::string timestamp = string_get_sortable_timestamp();
- const bool success = create_directory_with_parents(params.logdir);
+ const bool success = fs_create_directory_with_parents(params.logdir);
if (!success) {
fprintf(stderr, "%s: warning: failed to create logdir %s, cannot write logfile\n",
__func__, params.logdir.c_str());
@@ -80,7 +80,7 @@ static void write_logfile(
fprintf(logfile, "binary: main\n");
char model_desc[128];
llama_model_desc(model, model_desc, sizeof(model_desc));
- dump_non_result_info_yaml(logfile, params, ctx, timestamp, input_tokens, model_desc);
+ yaml_dump_non_result_info(logfile, params, ctx, timestamp, input_tokens, model_desc);
fprintf(logfile, "\n");
fprintf(logfile, "######################\n");
@@ -88,8 +88,8 @@ static void write_logfile(
fprintf(logfile, "######################\n");
fprintf(logfile, "\n");
- dump_string_yaml_multiline(logfile, "output", output.c_str());
- dump_vector_int_yaml(logfile, "output_tokens", output_tokens);
+ yaml_dump_string_multiline(logfile, "output", output.c_str());
+ yaml_dump_vector_int(logfile, "output_tokens", output_tokens);
llama_dump_timing_info_yaml(logfile, ctx);
fclose(logfile);
@@ -181,7 +181,7 @@ int main(int argc, char ** argv) {
std::mt19937 rng(params.seed);
if (params.random_prompt) {
- params.prompt = gpt_random_prompt(rng);
+ params.prompt = string_random_prompt(rng);
}
LOG("%s: llama backend init\n", __func__);
@@ -219,7 +219,7 @@ int main(int argc, char ** argv) {
// print system information
{
LOG_TEE("\n");
- LOG_TEE("%s\n", get_system_info(params).c_str());
+ LOG_TEE("%s\n", gpt_params_get_system_info(params).c_str());
}
std::string path_session = params.path_prompt_cache;
@@ -879,7 +879,7 @@ int main(int argc, char ** argv) {
embd_inp.insert(embd_inp.end(), cml_pfx.begin(), cml_pfx.end());
}
if (params.escape) {
- process_escapes(buffer);
+ string_process_escapes(buffer);
}
const auto line_pfx = ::llama_tokenize(ctx, params.input_prefix, false, true);
diff --git a/examples/parallel/parallel.cpp b/examples/parallel/parallel.cpp
index 7c5595d6..c731abb7 100644
--- a/examples/parallel/parallel.cpp
+++ b/examples/parallel/parallel.cpp
@@ -210,7 +210,7 @@ int main(int argc, char ** argv) {
while (true) {
if (dump_kv_cache) {
llama_kv_cache_view_update(ctx, &kvc_view);
- dump_kv_cache_view_seqs(kvc_view, 40);
+ llama_kv_cache_dump_view_seqs(kvc_view, 40);
}
llama_batch_clear(batch);
diff --git a/examples/perplexity/perplexity.cpp b/examples/perplexity/perplexity.cpp
index bae014e6..30e5e282 100644
--- a/examples/perplexity/perplexity.cpp
+++ b/examples/perplexity/perplexity.cpp
@@ -44,9 +44,9 @@ static void write_logfile(
return;
}
- const std::string timestamp = get_sortable_timestamp();
+ const std::string timestamp = string_get_sortable_timestamp();
- const bool success = create_directory_with_parents(params.logdir);
+ const bool success = fs_create_directory_with_parents(params.logdir);
if (!success) {
fprintf(stderr, "%s: warning: failed to create logdir %s, cannot write logfile\n",
__func__, params.logdir.c_str());
@@ -64,7 +64,7 @@ static void write_logfile(
fprintf(logfile, "binary: main\n");
char model_desc[128];
llama_model_desc(model, model_desc, sizeof(model_desc));
- dump_non_result_info_yaml(logfile, params, ctx, timestamp, results.tokens, model_desc);
+ yaml_dump_non_result_info(logfile, params, ctx, timestamp, results.tokens, model_desc);
fprintf(logfile, "\n");
fprintf(logfile, "######################\n");
@@ -72,9 +72,9 @@ static void write_logfile(
fprintf(logfile, "######################\n");
fprintf(logfile, "\n");
- dump_vector_float_yaml(logfile, "logits", results.logits);
+ yaml_dump_vector_float(logfile, "logits", results.logits);
fprintf(logfile, "ppl_value: %f\n", results.ppl_value);
- dump_vector_float_yaml(logfile, "probs", results.probs);
+ yaml_dump_vector_float(logfile, "probs", results.probs);
llama_dump_timing_info_yaml(logfile, ctx);
fclose(logfile);
@@ -2007,7 +2007,7 @@ int main(int argc, char ** argv) {
std::mt19937 rng(params.seed);
if (params.random_prompt) {
- params.prompt = gpt_random_prompt(rng);
+ params.prompt = string_random_prompt(rng);
}
llama_backend_init();
@@ -2035,7 +2035,7 @@ int main(int argc, char ** argv) {
// print system information
{
fprintf(stderr, "\n");
- fprintf(stderr, "%s\n", get_system_info(params).c_str());
+ fprintf(stderr, "%s\n", gpt_params_get_system_info(params).c_str());
}
struct results_perplexity results;
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp
index cbb45233..28584e14 100644
--- a/examples/quantize/quantize.cpp
+++ b/examples/quantize/quantize.cpp
@@ -259,7 +259,7 @@ int main(int argc, char ** argv) {
usage(argv[0]);
}
} else if (strcmp(argv[arg_idx], "--override-kv") == 0) {
- if (arg_idx == argc-1 || !parse_kv_override(argv[++arg_idx], kv_overrides)) {
+ if (arg_idx == argc-1 || !string_parse_kv_override(argv[++arg_idx], kv_overrides)) {
usage(argv[0]);
}
} else if (strcmp(argv[arg_idx], "--allow-requantize") == 0) {
diff --git a/examples/retrieval/retrieval.cpp b/examples/retrieval/retrieval.cpp
index 5ba71e76..4e753070 100644
--- a/examples/retrieval/retrieval.cpp
+++ b/examples/retrieval/retrieval.cpp
@@ -11,7 +11,7 @@ struct retrieval_params {
};
static void retrieval_params_print_usage(int argc, char ** argv, gpt_params & gpt_params, retrieval_params & params) {
- gpt_print_usage(argc, argv, gpt_params);
+ gpt_params_print_usage(argc, argv, gpt_params);
printf("retrieval options:\n");
printf(" --context-file FNAME file containing context to embed.\n");
printf(" specify multiple files by providing --context-file option multiple times.\n");
@@ -226,7 +226,7 @@ int main(int argc, char ** argv) {
// print system information
{
fprintf(stderr, "\n");
- fprintf(stderr, "%s\n", get_system_info(params).c_str());
+ fprintf(stderr, "%s\n", gpt_params_get_system_info(params).c_str());
}
// max batch size
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 6af5cb96..e9904263 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -1019,7 +1019,7 @@ struct server_context {
sampler_names.emplace_back(sampler_name);
}
}
- slot.sparams.samplers_sequence = sampler_types_from_names(sampler_names, false);
+ slot.sparams.samplers_sequence = llama_sampling_types_from_names(sampler_names, false);
} else {
slot.sparams.samplers_sequence = default_sparams.samplers_sequence;
}
@@ -1256,7 +1256,7 @@ struct server_context {
std::vector<std::string> samplers_sequence;
samplers_sequence.reserve(slot.sparams.samplers_sequence.size());
for (const auto & sampler_type : slot.sparams.samplers_sequence) {
- samplers_sequence.emplace_back(sampler_type_to_name_string(sampler_type));
+ samplers_sequence.emplace_back(llama_sampling_type_to_str(sampler_type));
}
return json {
@@ -2852,7 +2852,7 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
invalid_param = true;
break;
}
- if (!parse_kv_override(argv[i], params.kv_overrides)) {
+ if (!string_parse_kv_override(argv[i], params.kv_overrides)) {
fprintf(stderr, "error: Invalid type for KV override: %s\n", argv[i]);
invalid_param = true;
break;
@@ -3310,7 +3310,7 @@ int main(int argc, char ** argv) {
const auto handle_slots_save = [&ctx_server, &res_error, &sparams](const httplib::Request & req, httplib::Response & res, int id_slot) {
json request_data = json::parse(req.body);
std::string filename = request_data.at("filename");
- if (!validate_file_name(filename)) {
+ if (!fs_validate_filename(filename)) {
res_error(res, format_error_response("Invalid filename", ERROR_TYPE_INVALID_REQUEST));
return;
}
@@ -3340,7 +3340,7 @@ int main(int argc, char ** argv) {
const auto handle_slots_restore = [&ctx_server, &res_error, &sparams](const httplib::Request & req, httplib::Response & res, int id_slot) {
json request_data = json::parse(req.body);
std::string filename = request_data.at("filename");
- if (!validate_file_name(filename)) {
+ if (!fs_validate_filename(filename)) {
res_error(res, format_error_response("Invalid filename", ERROR_TYPE_INVALID_REQUEST));
return;
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-16 08:38:00 +0000