upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-06 18:10:51 -05:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into HEAD

Browse Source
This commit is contained in:
Georgi Gerganov
2025-12-18 10:12:47 +02:00
parent 981475fedc 57c1e05643
commit eefdb0da17
138 changed files with 7629 additions and 4541 deletions
Download Patch File Download Diff File Expand all files Collapse all files

182
common/arg.cpp
View File

@@ -420,6 +420,8 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
}
};
std::set<std::string> seen_args;
for (int i = 1; i < argc; i++) {
const std::string arg_prefix = "--";
@@ -430,6 +432,9 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
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;
@@ -750,6 +755,8 @@ bool common_params_to_map(int argc, char ** argv, llama_example ex, std::map<com
}
};
std::set<std::string> seen_args;
for (int i = 1; i < argc; i++) {
const std::string arg_prefix = "--";
@@ -760,6 +767,9 @@ bool common_params_to_map(int argc, char ** argv, llama_example ex, std::map<com
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) {
@@ -835,6 +845,19 @@ bool common_arg_utils::is_autoy(const std::string & value) {
}
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
@@ -1107,7 +1130,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_env("LLAMA_ARG_SWA_FULL"));
add_opt(common_arg(
{"--ctx-checkpoints", "--swa-checkpoints"}, "N",
string_format("max number of context checkpoints to create per slot (default: %d)\n"
string_format("max number of context checkpoints to create per slot (default: %d)"
"[(more info)](https://github.com/ggml-org/llama.cpp/pull/15293)", params.n_ctx_checkpoints),
[](common_params & params, int value) {
params.n_ctx_checkpoints = value;
@@ -1115,7 +1138,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_env("LLAMA_ARG_CTX_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"--cache-ram", "-cram"}, "N",
string_format("set the maximum cache size in MiB (default: %d, -1 - no limit, 0 - disable)\n"
string_format("set the maximum cache size in MiB (default: %d, -1 - no limit, 0 - disable)"
"[(more info)](https://github.com/ggml-org/llama.cpp/pull/16391)", params.cache_ram_mib),
[](common_params & params, int value) {
params.cache_ram_mib = value;
@@ -1123,12 +1146,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_env("LLAMA_ARG_CACHE_RAM").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"--kv-unified", "-kvu"},
string_format("use single unified KV buffer for the KV cache of all sequences (default: %s)\n"
"[(more info)](https://github.com/ggml-org/llama.cpp/pull/14363)", params.kv_unified ? "true" : "false"),
"use single unified KV buffer shared across all sequences (default: enabled if number of slots is auto)",
[](common_params & params) {
params.kv_unified = true;
}
).set_env("LLAMA_ARG_KV_UNIFIED"));
).set_env("LLAMA_ARG_KV_UNIFIED").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_PERPLEXITY}));
add_opt(common_arg(
{"--context-shift"},
{"--no-context-shift"},
@@ -1214,13 +1236,15 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_DIFFUSION}));
add_opt(common_arg(
{"--in-file"}, "FNAME",
"an input file (repeat to specify multiple files)",
"an input file (use comma-separated values to specify multiple files)",
[](common_params & params, const std::string & value) {
std::ifstream file(value);
if (!file) {
throw std::runtime_error(string_format("error: failed to open file '%s'\n", value.c_str()));
for (const auto & item : string_split<std::string>(value, ',')) {
std::ifstream file(item);
if (!file) {
throw std::runtime_error(string_format("error: failed to open file '%s'\n", item.c_str()));
}
params.in_files.push_back(item);
}
params.in_files.push_back(value);
}
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
add_opt(common_arg(
@@ -1895,13 +1919,27 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
LOG_WRN("DEPRECATED: --defrag-thold is deprecated and no longer necessary to specify\n");
}
).set_env("LLAMA_ARG_DEFRAG_THOLD"));
add_opt(common_arg(
{"-np", "--parallel"}, "N",
string_format("number of parallel sequences to decode (default: %d)", params.n_parallel),
[](common_params & params, int value) {
params.n_parallel = value;
}
).set_env("LLAMA_ARG_N_PARALLEL"));
if (ex == LLAMA_EXAMPLE_SERVER) {
// this is to make sure this option appears in the server-specific section of the help message
add_opt(common_arg(
{"-np", "--parallel"}, "N",
string_format("number of server slots (default: %d, -1 = auto)", params.n_parallel),
[](common_params & params, int value) {
if (value == 0) {
throw std::invalid_argument("error: invalid value for n_parallel\n");
}
params.n_parallel = value;
}
).set_env("LLAMA_ARG_N_PARALLEL").set_examples({LLAMA_EXAMPLE_SERVER}));
} else {
add_opt(common_arg(
{"-np", "--parallel"}, "N",
string_format("number of parallel sequences to decode (default: %d)", params.n_parallel),
[](common_params & params, int value) {
params.n_parallel = value;
}
).set_env("LLAMA_ARG_N_PARALLEL"));
}
add_opt(common_arg(
{"-ns", "--sequences"}, "N",
string_format("number of sequences to decode (default: %d)", params.n_sequences),
@@ -1950,9 +1988,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ_OFFLOAD"));
add_opt(common_arg(
{"--image", "--audio"}, "FILE",
"path to an image or audio file. use with multimodal models, can be repeated if you have multiple files\n",
"path to an image or audio file. use with multimodal models, use comma-separated values for multiple files\n",
[](common_params & params, const std::string & value) {
params.image.emplace_back(value);
for (const auto & item : string_split<std::string>(value, ',')) {
params.image.emplace_back(item);
}
}
).set_examples({LLAMA_EXAMPLE_MTMD, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
@@ -2199,12 +2239,39 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
));
add_opt(common_arg(
{"--override-kv"}, "KEY=TYPE:VALUE",
"advanced option to override model metadata by key. may be specified multiple times.\n"
"types: int, float, bool, str. example: --override-kv tokenizer.ggml.add_bos_token=bool:false",
{"--override-kv"}, "KEY=TYPE:VALUE,...",
"advanced option to override model metadata by key. to specify multiple overrides, either use comma-separated or repeat this argument.\n"
"types: int, float, bool, str. example: --override-kv tokenizer.ggml.add_bos_token=bool:false,tokenizer.ggml.add_eos_token=bool:false",
[](common_params & params, const std::string & value) {
if (!string_parse_kv_override(value.c_str(), params.kv_overrides)) {
throw std::runtime_error(string_format("error: Invalid type for KV override: %s\n", value.c_str()));
std::vector<std::string> kv_overrides;
std::string current;
bool escaping = false;
for (const char c : value) {
if (escaping) {
current.push_back(c);
escaping = false;
} else if (c == '\\') {
escaping = true;
} else if (c == ',') {
kv_overrides.push_back(current);
current.clear();
} else {
current.push_back(c);
}
}
if (escaping) {
current.push_back('\\');
}
kv_overrides.push_back(current);
for (const auto & kv_override : kv_overrides) {
if (!string_parse_kv_override(kv_override.c_str(), params.kv_overrides)) {
throw std::runtime_error(string_format("error: Invalid type for KV override: %s\n", kv_override.c_str()));
}
}
}
));
@@ -2218,33 +2285,50 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
));
add_opt(common_arg(
{"--lora"}, "FNAME",
"path to LoRA adapter (can be repeated to use multiple adapters)",
"path to LoRA adapter (use comma-separated values to load multiple adapters)",
[](common_params & params, const std::string & value) {
params.lora_adapters.push_back({ std::string(value), 1.0, "", "", nullptr });
for (const auto & item : string_split<std::string>(value, ',')) {
params.lora_adapters.push_back({ item, 1.0, "", "", nullptr });
}
}
// we define this arg on both COMMON and EXPORT_LORA, so when showing help message of export-lora, it will be categorized as "example-specific" arg
).set_examples({LLAMA_EXAMPLE_COMMON, LLAMA_EXAMPLE_EXPORT_LORA}));
add_opt(common_arg(
{"--lora-scaled"}, "FNAME", "SCALE",
"path to LoRA adapter with user defined scaling (can be repeated to use multiple adapters)",
[](common_params & params, const std::string & fname, const std::string & scale) {
params.lora_adapters.push_back({ fname, std::stof(scale), "", "", nullptr });
{"--lora-scaled"}, "FNAME:SCALE,...",
"path to LoRA adapter with user defined scaling (format: FNAME:SCALE,...)\n"
"note: use comma-separated values",
[](common_params & params, const std::string & value) {
for (const auto & item : string_split<std::string>(value, ',')) {
auto parts = string_split<std::string>(item, ':');
if (parts.size() != 2) {
throw std::invalid_argument("lora-scaled format: FNAME:SCALE");
}
params.lora_adapters.push_back({ parts[0], std::stof(parts[1]), "", "", nullptr });
}
}
// we define this arg on both COMMON and EXPORT_LORA, so when showing help message of export-lora, it will be categorized as "example-specific" arg
).set_examples({LLAMA_EXAMPLE_COMMON, LLAMA_EXAMPLE_EXPORT_LORA}));
add_opt(common_arg(
{"--control-vector"}, "FNAME",
"add a control vector\nnote: this argument can be repeated to add multiple control vectors",
"add a control vector\nnote: use comma-separated values to add multiple control vectors",
[](common_params & params, const std::string & value) {
params.control_vectors.push_back({ 1.0f, value, });
for (const auto & item : string_split<std::string>(value, ',')) {
params.control_vectors.push_back({ 1.0f, item, });
}
}
));
add_opt(common_arg(
{"--control-vector-scaled"}, "FNAME", "SCALE",
{"--control-vector-scaled"}, "FNAME:SCALE,...",
"add a control vector with user defined scaling SCALE\n"
"note: this argument can be repeated to add multiple scaled control vectors",
[](common_params & params, const std::string & fname, const std::string & scale) {
params.control_vectors.push_back({ std::stof(scale), fname });
"note: use comma-separated values (format: FNAME:SCALE,...)",
[](common_params & params, const std::string & value) {
for (const auto & item : string_split<std::string>(value, ',')) {
auto parts = string_split<std::string>(item, ':');
if (parts.size() != 2) {
throw std::invalid_argument("control-vector-scaled format: FNAME:SCALE");
}
params.control_vectors.push_back({ std::stof(parts[1]), parts[0] });
}
}
));
add_opt(common_arg(
@@ -2334,13 +2418,15 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_env("HF_TOKEN"));
add_opt(common_arg(
{"--context-file"}, "FNAME",
"file to load context from (repeat to specify multiple files)",
"file to load context from (use comma-separated values to specify multiple files)",
[](common_params & params, const std::string & value) {
std::ifstream file(value, std::ios::binary);
if (!file) {
throw std::runtime_error(string_format("error: failed to open file '%s'\n", value.c_str()));
for (const auto & item : string_split<std::string>(value, ',')) {
std::ifstream file(item, std::ios::binary);
if (!file) {
throw std::runtime_error(string_format("error: failed to open file '%s'\n", item.c_str()));
}
params.context_files.push_back(item);
}
params.context_files.push_back(value);
}
).set_examples({LLAMA_EXAMPLE_RETRIEVAL}));
add_opt(common_arg(
@@ -2531,6 +2617,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.api_prefix = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_API_PREFIX"));
add_opt(common_arg(
{"--webui-config"}, "JSON",
"JSON that provides default WebUI settings (overrides WebUI defaults)",
[](common_params & params, const std::string & value) {
params.webui_config_json = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_WEBUI_CONFIG"));
add_opt(common_arg(
{"--webui-config-file"}, "PATH",
"JSON file that provides default WebUI settings (overrides WebUI defaults)",
[](common_params & params, const std::string & value) {
params.webui_config_json = read_file(value);
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_WEBUI_CONFIG_FILE"));
add_opt(common_arg(
{"--webui"},
{"--no-webui"},