common : normalize naming style (#7462)
* common : normalize naming style ggml-ci * common : match declaration / definition order * zig : try to fix build
This commit is contained in:
Georgi Gerganov
GitHub
parent
38c03478a3
commit
6ff13987ad
21 changed files with 823 additions and 793 deletions
1338
common/common.cpp
1338
common/common.cpp
File diff suppressed because it is too large
Load diff
|
|
@ -27,7 +27,7 @@
|
|||
#define die_fmt(fmt, ...) do { fprintf(stderr, "error: " fmt "\n", __VA_ARGS__); exit(1); } while (0)
|
||||
|
||||
#define print_build_info() do { \
|
||||
fprintf(stderr, "%s: build = %d (%s)\n", __func__, LLAMA_BUILD_NUMBER, LLAMA_COMMIT); \
|
||||
fprintf(stderr, "%s: build = %d (%s)\n", __func__, LLAMA_BUILD_NUMBER, LLAMA_COMMIT); \
|
||||
fprintf(stderr, "%s: built with %s for %s\n", __func__, LLAMA_COMPILER, LLAMA_BUILD_TARGET); \
|
||||
} while(0)
|
||||
|
||||
|
|
@ -35,14 +35,18 @@
|
|||
|
||||
// build info
|
||||
extern int LLAMA_BUILD_NUMBER;
|
||||
extern char const *LLAMA_COMMIT;
|
||||
extern char const *LLAMA_COMPILER;
|
||||
extern char const *LLAMA_BUILD_TARGET;
|
||||
extern char const * LLAMA_COMMIT;
|
||||
extern char const * LLAMA_COMPILER;
|
||||
extern char const * LLAMA_BUILD_TARGET;
|
||||
|
||||
struct llama_control_vector_load_info;
|
||||
|
||||
int get_math_cpu_count();
|
||||
int32_t get_num_physical_cores();
|
||||
//
|
||||
// CPU utils
|
||||
//
|
||||
|
||||
int32_t cpu_get_num_physical_cores();
|
||||
int32_t cpu_get_num_math();
|
||||
|
||||
//
|
||||
// CLI argument parsing
|
||||
|
|
@ -51,7 +55,7 @@ int32_t get_num_physical_cores();
|
|||
struct gpt_params {
|
||||
uint32_t seed = LLAMA_DEFAULT_SEED; // RNG seed
|
||||
|
||||
int32_t n_threads = get_math_cpu_count();
|
||||
int32_t n_threads = cpu_get_num_math();
|
||||
int32_t n_threads_draft = -1;
|
||||
int32_t n_threads_batch = -1; // number of threads to use for batch processing (-1 = use n_threads)
|
||||
int32_t n_threads_batch_draft = -1;
|
||||
|
|
@ -179,33 +183,34 @@ struct gpt_params {
|
|||
|
||||
void gpt_params_handle_model_default(gpt_params & params);
|
||||
|
||||
bool parse_kv_override(const char * data, std::vector<llama_model_kv_override> & overrides);
|
||||
bool gpt_params_parse_ex (int argc, char ** argv, gpt_params & params);
|
||||
bool gpt_params_parse (int argc, char ** argv, gpt_params & params);
|
||||
bool gpt_params_find_arg (int argc, char ** argv, const std::string & arg, gpt_params & params, int & i, bool & invalid_param);
|
||||
void gpt_params_print_usage(int argc, char ** argv, const gpt_params & params);
|
||||
|
||||
bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params);
|
||||
|
||||
bool gpt_params_parse(int argc, char ** argv, gpt_params & params);
|
||||
|
||||
void gpt_print_usage(int argc, char ** argv, const gpt_params & params);
|
||||
|
||||
bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_params & params, int & i, bool & invalid_param);
|
||||
|
||||
std::string get_system_info(const gpt_params & params);
|
||||
|
||||
std::string gpt_random_prompt(std::mt19937 & rng);
|
||||
|
||||
void process_escapes(std::string& input);
|
||||
|
||||
bool validate_file_name(const std::string & filename);
|
||||
std::string gpt_params_get_system_info(const gpt_params & params);
|
||||
|
||||
//
|
||||
// String utils
|
||||
//
|
||||
|
||||
std::vector<llama_sampler_type> sampler_types_from_names(const std::vector<std::string> & names, bool allow_alt_names);
|
||||
std::vector<llama_sampler_type> sampler_types_from_chars(const std::string & names_string);
|
||||
std::vector<std::string> string_split(std::string input, char separator);
|
||||
|
||||
std::string string_strip(const std::string & str);
|
||||
std::string sampler_type_to_name_string(llama_sampler_type sampler_type);
|
||||
std::string string_get_sortable_timestamp();
|
||||
std::string string_random_prompt(std::mt19937 & rng);
|
||||
|
||||
bool string_parse_kv_override(const char * data, std::vector<llama_model_kv_override> & overrides);
|
||||
void string_process_escapes(std::string & input);
|
||||
|
||||
//
|
||||
// Filesystem utils
|
||||
//
|
||||
|
||||
bool fs_validate_filename(const std::string & filename);
|
||||
bool fs_create_directory_with_parents(const std::string & path);
|
||||
|
||||
std::string fs_get_cache_directory();
|
||||
|
||||
//
|
||||
// Model utils
|
||||
|
|
@ -276,30 +281,15 @@ std::string llama_detokenize_bpe(
|
|||
// defaults to true when model type is SPM, otherwise false.
|
||||
bool llama_should_add_bos_token(const llama_model * model);
|
||||
|
||||
//
|
||||
// YAML utils
|
||||
//
|
||||
|
||||
bool create_directory_with_parents(const std::string & path);
|
||||
std::string get_cache_directory();
|
||||
void dump_vector_float_yaml(FILE * stream, const char * prop_name, const std::vector<float> & data);
|
||||
void dump_vector_int_yaml(FILE * stream, const char * prop_name, const std::vector<int> & data);
|
||||
void dump_string_yaml_multiline(FILE * stream, const char * prop_name, const char * data);
|
||||
std::string get_sortable_timestamp();
|
||||
|
||||
void dump_non_result_info_yaml(
|
||||
FILE * stream, const gpt_params & params, const llama_context * lctx,
|
||||
const std::string & timestamp, const std::vector<int> & prompt_tokens, const char * model_desc);
|
||||
|
||||
//
|
||||
// KV cache utils
|
||||
//
|
||||
|
||||
// Dump the KV cache view with the number of sequences per cell.
|
||||
void dump_kv_cache_view(const llama_kv_cache_view & view, int row_size = 80);
|
||||
void llama_kv_cache_dump_view(const llama_kv_cache_view & view, int row_size = 80);
|
||||
|
||||
// Dump the KV cache view showing individual sequences in each cell (long output).
|
||||
void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size = 40);
|
||||
void llama_kv_cache_dump_view_seqs(const llama_kv_cache_view & view, int row_size = 40);
|
||||
|
||||
//
|
||||
// Embedding utils
|
||||
|
|
@ -333,6 +323,20 @@ llama_control_vector_data llama_control_vector_load(const std::vector<llama_cont
|
|||
//
|
||||
// Split utils
|
||||
//
|
||||
|
||||
static const char * const LLM_KV_SPLIT_NO = "split.no";
|
||||
static const char * const LLM_KV_SPLIT_COUNT = "split.count";
|
||||
static const char * const LLM_KV_SPLIT_TENSORS_COUNT = "split.tensors.count";
|
||||
|
||||
//
|
||||
// YAML utils
|
||||
//
|
||||
|
||||
void yaml_dump_vector_float (FILE * stream, const char * prop_name, const std::vector<float> & data);
|
||||
void yaml_dump_vector_int (FILE * stream, const char * prop_name, const std::vector<int> & data);
|
||||
void yaml_dump_string_multiline(FILE * stream, const char * prop_name, const char * data);
|
||||
|
||||
void yaml_dump_non_result_info(
|
||||
FILE * stream, const gpt_params & params, const llama_context * lctx,
|
||||
const std::string & timestamp, const std::vector<int> & prompt_tokens, const char * model_desc);
|
||||
|
||||
|
|
|
|||
|
|
@ -125,7 +125,7 @@ std::string llama_sampling_order_print(const llama_sampling_params & params) {
|
|||
std::string result = "CFG -> Penalties ";
|
||||
if (params.mirostat == 0) {
|
||||
for (auto sampler_type : params.samplers_sequence) {
|
||||
const auto sampler_type_name = sampler_type_to_name_string(sampler_type);
|
||||
const auto sampler_type_name = llama_sampling_type_to_str(sampler_type);
|
||||
if (!sampler_type_name.empty()) {
|
||||
result += "-> " + sampler_type_name + " ";
|
||||
}
|
||||
|
|
@ -137,6 +137,87 @@ std::string llama_sampling_order_print(const llama_sampling_params & params) {
|
|||
return result;
|
||||
}
|
||||
|
||||
std::string llama_sampling_type_to_str(llama_sampler_type sampler_type) {
|
||||
switch (sampler_type) {
|
||||
case llama_sampler_type::TOP_K: return "top_k";
|
||||
case llama_sampler_type::TFS_Z: return "tfs_z";
|
||||
case llama_sampler_type::TYPICAL_P: return "typical_p";
|
||||
case llama_sampler_type::TOP_P: return "top_p";
|
||||
case llama_sampler_type::MIN_P: return "min_p";
|
||||
case llama_sampler_type::TEMPERATURE: return "temperature";
|
||||
default : return "";
|
||||
}
|
||||
}
|
||||
|
||||
std::vector<llama_sampler_type> llama_sampling_types_from_names(const std::vector<std::string> & names, bool allow_alt_names) {
|
||||
std::unordered_map<std::string, llama_sampler_type> sampler_canonical_name_map {
|
||||
{"top_k", llama_sampler_type::TOP_K},
|
||||
{"top_p", llama_sampler_type::TOP_P},
|
||||
{"typical_p", llama_sampler_type::TYPICAL_P},
|
||||
{"min_p", llama_sampler_type::MIN_P},
|
||||
{"tfs_z", llama_sampler_type::TFS_Z},
|
||||
{"temperature", llama_sampler_type::TEMPERATURE}
|
||||
};
|
||||
|
||||
// since samplers names are written multiple ways
|
||||
// make it ready for both system names and input names
|
||||
std::unordered_map<std::string, llama_sampler_type> sampler_alt_name_map {
|
||||
{"top-k", llama_sampler_type::TOP_K},
|
||||
{"top-p", llama_sampler_type::TOP_P},
|
||||
{"nucleus", llama_sampler_type::TOP_P},
|
||||
{"typical-p", llama_sampler_type::TYPICAL_P},
|
||||
{"typical", llama_sampler_type::TYPICAL_P},
|
||||
{"min-p", llama_sampler_type::MIN_P},
|
||||
{"tfs-z", llama_sampler_type::TFS_Z},
|
||||
{"tfs", llama_sampler_type::TFS_Z},
|
||||
{"temp", llama_sampler_type::TEMPERATURE}
|
||||
};
|
||||
|
||||
std::vector<llama_sampler_type> sampler_types;
|
||||
sampler_types.reserve(names.size());
|
||||
for (const auto & name : names)
|
||||
{
|
||||
auto sampler_item = sampler_canonical_name_map.find(name);
|
||||
if (sampler_item != sampler_canonical_name_map.end())
|
||||
{
|
||||
sampler_types.push_back(sampler_item->second);
|
||||
}
|
||||
else
|
||||
{
|
||||
if (allow_alt_names)
|
||||
{
|
||||
sampler_item = sampler_alt_name_map.find(name);
|
||||
if (sampler_item != sampler_alt_name_map.end())
|
||||
{
|
||||
sampler_types.push_back(sampler_item->second);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return sampler_types;
|
||||
}
|
||||
|
||||
std::vector<llama_sampler_type> llama_sampling_types_from_chars(const std::string & names_string) {
|
||||
std::unordered_map<char, llama_sampler_type> sampler_name_map {
|
||||
{'k', llama_sampler_type::TOP_K},
|
||||
{'p', llama_sampler_type::TOP_P},
|
||||
{'y', llama_sampler_type::TYPICAL_P},
|
||||
{'m', llama_sampler_type::MIN_P},
|
||||
{'f', llama_sampler_type::TFS_Z},
|
||||
{'t', llama_sampler_type::TEMPERATURE}
|
||||
};
|
||||
|
||||
std::vector<llama_sampler_type> sampler_types;
|
||||
sampler_types.reserve(names_string.size());
|
||||
for (const auto & c : names_string) {
|
||||
const auto sampler_item = sampler_name_map.find(c);
|
||||
if (sampler_item != sampler_name_map.end()) {
|
||||
sampler_types.push_back(sampler_item->second);
|
||||
}
|
||||
}
|
||||
return sampler_types;
|
||||
}
|
||||
|
||||
// no reasons to expose this function in header
|
||||
static void sampler_queue(
|
||||
struct llama_context * ctx_main,
|
||||
|
|
|
|||
|
|
@ -116,6 +116,11 @@ std::string llama_sampling_print(const llama_sampling_params & params);
|
|||
// Print sampling order into a string
|
||||
std::string llama_sampling_order_print(const llama_sampling_params & params);
|
||||
|
||||
std::string llama_sampling_type_to_str(llama_sampler_type sampler_type);
|
||||
|
||||
std::vector<llama_sampler_type> llama_sampling_types_from_names(const std::vector<std::string> & names, bool allow_alt_names);
|
||||
std::vector<llama_sampler_type> llama_sampling_types_from_chars(const std::string & names_string);
|
||||
|
||||
// this is a common sampling function used across the examples for convenience
|
||||
// it can serve as a starting point for implementing your own sampling function
|
||||
// Note: When using multiple sequences, it is the caller's responsibility to call
|
||||
|
|
|
|||
|
|
@ -1380,7 +1380,7 @@ bool consume_common_train_arg(
|
|||
|
||||
void finish_processing_train_args(struct train_params_common * params) {
|
||||
if (params->escape) {
|
||||
process_escapes(params->sample_start);
|
||||
string_process_escapes(params->sample_start);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue