common: support negated args (#17919)
* args: support negated args * update docs * fix typo * add more neg options * Apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * rm duplicated arg * fix LLAMA_ARG_NO_HOST * add test --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Xuan-Son Nguyen
GitHub
parent
e39a2ce66d
commit
380b4c984e
6 changed files with 235 additions and 161 deletions
290
common/arg.cpp
290
common/arg.cpp
|
|
@ -105,6 +105,16 @@ bool common_arg::is_exclude(enum llama_example ex) {
|
|||
|
||||
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;
|
||||
|
|
@ -114,6 +124,14 @@ bool common_arg::get_value_from_env(std::string & output) const {
|
|||
}
|
||||
|
||||
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);
|
||||
}
|
||||
|
||||
|
|
@ -151,9 +169,10 @@ std::string common_arg::to_string() const {
|
|||
std::string leading_spaces(n_leading_spaces, ' ');
|
||||
|
||||
std::ostringstream ss;
|
||||
for (const auto arg : args) {
|
||||
if (arg == args.front()) {
|
||||
if (args.size() == 1) {
|
||||
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
|
||||
|
|
@ -162,7 +181,7 @@ std::string common_arg::to_string() const {
|
|||
ss << tmp << spaces;
|
||||
}
|
||||
} else {
|
||||
ss << arg << (arg != args.back() ? ", " : "");
|
||||
ss << arg << (arg != all_args.back() ? ", " : "");
|
||||
}
|
||||
}
|
||||
if (value_hint) ss << " " << value_hint;
|
||||
|
|
@ -181,6 +200,31 @@ std::string common_arg::to_string() const {
|
|||
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
|
||||
//
|
||||
|
|
@ -316,6 +360,16 @@ static std::string get_all_kv_cache_types() {
|
|||
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
|
||||
//
|
||||
|
|
@ -323,10 +377,13 @@ static std::string get_all_kv_cache_types() {
|
|||
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, common_arg *> arg_to_options;
|
||||
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;
|
||||
arg_to_options[arg] = {&opt, /* is_positive */ true};
|
||||
}
|
||||
for (const auto & arg : opt.args_neg) {
|
||||
arg_to_options[arg] = {&opt, /* is_positive */ false};
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -335,12 +392,15 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
|
|||
std::string value;
|
||||
if (opt.get_value_from_env(value)) {
|
||||
try {
|
||||
if (opt.handler_void && (value == "1" || value == "true")) {
|
||||
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;
|
||||
|
|
@ -369,7 +429,9 @@ 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()));
|
||||
}
|
||||
auto opt = *arg_to_options[arg];
|
||||
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());
|
||||
}
|
||||
|
|
@ -378,6 +440,10 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
|
|||
opt.handler_void(params);
|
||||
continue;
|
||||
}
|
||||
if (opt.handler_bool) {
|
||||
opt.handler_bool(params, is_positive);
|
||||
continue;
|
||||
}
|
||||
|
||||
// arg with single value
|
||||
check_arg(i);
|
||||
|
|
@ -402,7 +468,7 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
|
|||
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(), arg_to_options[arg]->to_string().c_str()));
|
||||
arg.c_str(), e.what(), opt.to_string().c_str()));
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -750,11 +816,11 @@ static std::string list_builtin_chat_templates() {
|
|||
}
|
||||
|
||||
bool common_arg_utils::is_truthy(const std::string & value) {
|
||||
return value == "on" || value == "enabled" || value == "1";
|
||||
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 == "0";
|
||||
return value == "off" || value == "disabled" || value == "false" || value == "0";
|
||||
}
|
||||
|
||||
bool common_arg_utils::is_autoy(const std::string & value) {
|
||||
|
|
@ -839,10 +905,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
}
|
||||
));
|
||||
add_opt(common_arg(
|
||||
{"--display-prompt"},
|
||||
{"--no-display-prompt"},
|
||||
string_format("don't print prompt at generation (default: %s)", !params.display_prompt ? "true" : "false"),
|
||||
[](common_params & params) {
|
||||
params.display_prompt = false;
|
||||
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(
|
||||
|
|
@ -1055,18 +1122,12 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
params.kv_unified = true;
|
||||
}
|
||||
).set_env("LLAMA_ARG_KV_UNIFIED"));
|
||||
add_opt(common_arg(
|
||||
{"--no-context-shift"},
|
||||
string_format("disables context shift on infinite text generation (default: %s)", params.ctx_shift ? "disabled" : "enabled"),
|
||||
[](common_params & params) {
|
||||
params.ctx_shift = false;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_PERPLEXITY}).set_env("LLAMA_ARG_NO_CONTEXT_SHIFT"));
|
||||
add_opt(common_arg(
|
||||
{"--context-shift"},
|
||||
string_format("enables context shift on infinite text generation (default: %s)", params.ctx_shift ? "enabled" : "disabled"),
|
||||
[](common_params & params) {
|
||||
params.ctx_shift = true;
|
||||
{"--no-context-shift"},
|
||||
string_format("whether to use context shift on infinite text generation (default: %s)", params.ctx_shift ? "enabled" : "disabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.ctx_shift = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_PERPLEXITY}).set_env("LLAMA_ARG_CONTEXT_SHIFT"));
|
||||
add_opt(common_arg(
|
||||
|
|
@ -1106,20 +1167,22 @@ 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(
|
||||
{"--perf"},
|
||||
{"--no-perf"},
|
||||
string_format("disable internal libllama performance timings (default: %s)", params.no_perf ? "true" : "false"),
|
||||
[](common_params & params) {
|
||||
params.no_perf = true;
|
||||
params.sampling.no_perf = true;
|
||||
string_format("whether to enable internal libllama performance timings (default: %s)", params.no_perf ? "true" : "false"),
|
||||
[](common_params & params, bool value) {
|
||||
params.no_perf = !value;
|
||||
params.sampling.no_perf = !value;
|
||||
}
|
||||
).set_env("LLAMA_ARG_NO_PERF"));
|
||||
).set_env("LLAMA_ARG_PERF"));
|
||||
add_opt(common_arg(
|
||||
{"--show-timings"},
|
||||
{"--no-show-timings"},
|
||||
string_format("disable timing information after each response (default: %s)", params.show_timings ? "true" : "false"),
|
||||
[](common_params & params) {
|
||||
params.show_timings = false;
|
||||
string_format("whether to show timing information after each response (default: %s)", params.show_timings ? "true" : "false"),
|
||||
[](common_params & params, bool value) {
|
||||
params.show_timings = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_NO_SHOW_TIMINGS"));
|
||||
).set_examples({LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_SHOW_TIMINGS"));
|
||||
add_opt(common_arg(
|
||||
{"-f", "--file"}, "FNAME",
|
||||
"a file containing the prompt (default: none)",
|
||||
|
|
@ -1171,16 +1234,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
).set_excludes({LLAMA_EXAMPLE_SERVER}));
|
||||
add_opt(common_arg(
|
||||
{"-e", "--escape"},
|
||||
string_format("process escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\) (default: %s)", params.escape ? "true" : "false"),
|
||||
[](common_params & params) {
|
||||
params.escape = true;
|
||||
}
|
||||
));
|
||||
add_opt(common_arg(
|
||||
{"--no-escape"},
|
||||
"do not process escape sequences",
|
||||
[](common_params & params) {
|
||||
params.escape = false;
|
||||
string_format("whether to process escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\) (default: %s)", params.escape ? "true" : "false"),
|
||||
[](common_params & params, bool value) {
|
||||
params.escape = value;
|
||||
}
|
||||
));
|
||||
add_opt(common_arg(
|
||||
|
|
@ -1227,19 +1284,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER}));
|
||||
add_opt(common_arg(
|
||||
{"-cnv", "--conversation"},
|
||||
"run in conversation mode:\n"
|
||||
{"-no-cnv", "--no-conversation"},
|
||||
"whether to run in conversation mode:\n"
|
||||
"- does not print special tokens and suffix/prefix\n"
|
||||
"- interactive mode is also enabled\n"
|
||||
"(default: auto enabled if chat template is available)",
|
||||
[](common_params & params) {
|
||||
params.conversation_mode = COMMON_CONVERSATION_MODE_ENABLED;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_COMPLETION}));
|
||||
add_opt(common_arg(
|
||||
{"-no-cnv", "--no-conversation"},
|
||||
"force disable conversation mode (default: false)",
|
||||
[](common_params & params) {
|
||||
params.conversation_mode = COMMON_CONVERSATION_MODE_DISABLED;
|
||||
[](common_params & params, bool value) {
|
||||
params.conversation_mode = value ? COMMON_CONVERSATION_MODE_ENABLED : COMMON_CONVERSATION_MODE_DISABLED;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}));
|
||||
add_opt(common_arg(
|
||||
|
|
@ -1297,10 +1348,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
}
|
||||
).set_examples({LLAMA_EXAMPLE_COMPLETION}));
|
||||
add_opt(common_arg(
|
||||
{"--warmup"},
|
||||
{"--no-warmup"},
|
||||
"skip warming up the model with an empty run",
|
||||
[](common_params & params) {
|
||||
params.warmup = false;
|
||||
string_format("whether to perform warmup with an empty run (default: %s)", params.warmup ? "enabled" : "disabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.warmup = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_MTMD, LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_RETRIEVAL, LLAMA_EXAMPLE_PERPLEXITY}));
|
||||
add_opt(common_arg(
|
||||
|
|
@ -1702,19 +1754,21 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
}
|
||||
).set_env("LLAMA_ARG_GRP_ATTN_W").set_examples({LLAMA_EXAMPLE_COMPLETION}));
|
||||
add_opt(common_arg(
|
||||
{"-kvo", "--kv-offload"},
|
||||
{"-nkvo", "--no-kv-offload"},
|
||||
"disable KV offload",
|
||||
[](common_params & params) {
|
||||
params.no_kv_offload = true;
|
||||
string_format("whether to enable KV cache offloading (default: %s)", params.no_kv_offload ? "disabled" : "enabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.no_kv_offload = !value;
|
||||
}
|
||||
).set_env("LLAMA_ARG_NO_KV_OFFLOAD"));
|
||||
).set_env("LLAMA_ARG_KV_OFFLOAD"));
|
||||
add_opt(common_arg(
|
||||
{"--repack"},
|
||||
{"-nr", "--no-repack"},
|
||||
"disable weight repacking",
|
||||
[](common_params & params) {
|
||||
params.no_extra_bufts = true;
|
||||
string_format("whether to enable weight repacking (default: %s)", params.no_extra_bufts ? "disabled" : "enabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.no_extra_bufts = !value;
|
||||
}
|
||||
).set_env("LLAMA_ARG_NO_REPACK"));
|
||||
).set_env("LLAMA_ARG_REPACK"));
|
||||
add_opt(common_arg(
|
||||
{"--no-host"},
|
||||
"bypass host buffer allowing extra buffers to be used",
|
||||
|
|
@ -1843,18 +1897,12 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
).set_examples({LLAMA_EXAMPLE_PARALLEL}));
|
||||
add_opt(common_arg(
|
||||
{"-cb", "--cont-batching"},
|
||||
string_format("enable continuous batching (a.k.a dynamic batching) (default: %s)", params.cont_batching ? "enabled" : "disabled"),
|
||||
[](common_params & params) {
|
||||
params.cont_batching = true;
|
||||
{"-nocb", "--no-cont-batching"},
|
||||
string_format("whether to enable continuous batching (a.k.a dynamic batching) (default: %s)", params.cont_batching ? "enabled" : "disabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.cont_batching = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_CONT_BATCHING"));
|
||||
add_opt(common_arg(
|
||||
{"-nocb", "--no-cont-batching"},
|
||||
"disable continuous batching",
|
||||
[](common_params & params) {
|
||||
params.cont_batching = false;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_CONT_BATCHING"));
|
||||
add_opt(common_arg(
|
||||
{"-mm", "--mmproj"}, "FILE",
|
||||
"path to a multimodal projector file. see tools/mtmd/README.md\n"
|
||||
|
|
@ -1871,19 +1919,21 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
}
|
||||
).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ_URL"));
|
||||
add_opt(common_arg(
|
||||
{"--no-mmproj"},
|
||||
"explicitly disable multimodal projector, useful when using -hf",
|
||||
[](common_params & params) {
|
||||
params.no_mmproj = true;
|
||||
{"--mmproj-auto"},
|
||||
{"--no-mmproj", "--no-mmproj-auto"},
|
||||
string_format("whether to use multimodal projector file (if available), useful when using -hf (default: %s)", params.no_mmproj ? "disabled" : "enabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.no_mmproj = !value;
|
||||
}
|
||||
).set_examples(mmproj_examples).set_env("LLAMA_ARG_NO_MMPROJ"));
|
||||
).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ_AUTO"));
|
||||
add_opt(common_arg(
|
||||
{"--mmproj-offload"},
|
||||
{"--no-mmproj-offload"},
|
||||
"do not offload multimodal projector to GPU",
|
||||
[](common_params & params) {
|
||||
params.mmproj_use_gpu = false;
|
||||
string_format("whether to enable GPU offloading for multimodal projector (default: %s)", params.mmproj_use_gpu ? "enabled" : "disabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.mmproj_use_gpu = value;
|
||||
}
|
||||
).set_examples(mmproj_examples).set_env("LLAMA_ARG_NO_MMPROJ_OFFLOAD"));
|
||||
).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",
|
||||
|
|
@ -1923,12 +1973,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
}
|
||||
).set_env("LLAMA_ARG_MLOCK"));
|
||||
add_opt(common_arg(
|
||||
{"--mmap"},
|
||||
{"--no-mmap"},
|
||||
"do not memory-map model (slower load but may reduce pageouts if not using mlock)",
|
||||
[](common_params & params) {
|
||||
params.use_mmap = false;
|
||||
string_format("whether to memory-map model (if disabled, slower load but may reduce pageouts if not using mlock) (default: %s)", params.use_mmap ? "enabled" : "disabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.use_mmap = value;
|
||||
}
|
||||
).set_env("LLAMA_ARG_NO_MMAP"));
|
||||
).set_env("LLAMA_ARG_MMAP"));
|
||||
add_opt(common_arg(
|
||||
{"--numa"}, "TYPE",
|
||||
"attempt optimizations that help on some NUMA systems\n"
|
||||
|
|
@ -2116,10 +2167,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
}
|
||||
));
|
||||
add_opt(common_arg(
|
||||
{"--op-offload"},
|
||||
{"--no-op-offload"},
|
||||
string_format("disable offloading host tensor operations to device (default: %s)", params.no_op_offload ? "true" : "false"),
|
||||
[](common_params & params) {
|
||||
params.no_op_offload = true;
|
||||
string_format("whether to offload host tensor operations to device (default: %s)", params.no_op_offload ? "false" : "true"),
|
||||
[](common_params & params, bool value) {
|
||||
params.no_op_offload = !value;
|
||||
}
|
||||
));
|
||||
add_opt(common_arg(
|
||||
|
|
@ -2315,10 +2367,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
}
|
||||
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
|
||||
add_opt(common_arg(
|
||||
{"--ppl"},
|
||||
{"--no-ppl"},
|
||||
string_format("do not compute perplexity (default: %s)", params.compute_ppl ? "true" : "false"),
|
||||
[](common_params & params) {
|
||||
params.compute_ppl = false;
|
||||
string_format("whether to compute perplexity (default: %s)", params.compute_ppl ? "true" : "false"),
|
||||
[](common_params & params, bool value) {
|
||||
params.compute_ppl = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
|
||||
add_opt(common_arg(
|
||||
|
|
@ -2437,12 +2490,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_API_PREFIX"));
|
||||
add_opt(common_arg(
|
||||
{"--webui"},
|
||||
{"--no-webui"},
|
||||
string_format("Disable the Web UI (default: %s)", params.webui ? "enabled" : "disabled"),
|
||||
[](common_params & params) {
|
||||
params.webui = false;
|
||||
string_format("whether to enable the Web UI (default: %s)", params.webui ? "enabled" : "disabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.webui = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_WEBUI"));
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_WEBUI"));
|
||||
add_opt(common_arg(
|
||||
{"--embedding", "--embeddings"},
|
||||
string_format("restrict to only support embedding use case; use only with dedicated embedding models (default: %s)", params.embedding ? "enabled" : "disabled"),
|
||||
|
|
@ -2547,18 +2601,12 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_PROPS"));
|
||||
add_opt(common_arg(
|
||||
{"--slots"},
|
||||
string_format("enable slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled"),
|
||||
[](common_params & params) {
|
||||
params.endpoint_slots = true;
|
||||
{"--no-slots"},
|
||||
string_format("expose slots monitoring endpoint (default: %s)", params.endpoint_slots ? "enabled" : "disabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.endpoint_slots = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ENDPOINT_SLOTS"));
|
||||
add_opt(common_arg(
|
||||
{"--no-slots"},
|
||||
"disables slots monitoring endpoint",
|
||||
[](common_params & params) {
|
||||
params.endpoint_slots = false;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_ENDPOINT_SLOTS"));
|
||||
add_opt(common_arg(
|
||||
{"--slot-save-path"}, "PATH",
|
||||
"path to save slot kv cache (default: disabled)",
|
||||
|
|
@ -2609,26 +2657,21 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MODELS_MAX"));
|
||||
add_opt(common_arg(
|
||||
{"--models-autoload"},
|
||||
{"--no-models-autoload"},
|
||||
"disables automatic loading of models (default: enabled)",
|
||||
[](common_params & params) {
|
||||
params.models_autoload = false;
|
||||
string_format("for router server, whether to automatically load models (default: %s)", params.models_autoload ? "enabled" : "disabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.models_autoload = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_MODELS_AUTOLOAD"));
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MODELS_AUTOLOAD"));
|
||||
add_opt(common_arg(
|
||||
{"--jinja"},
|
||||
string_format("use jinja template for chat (default: %s)", params.use_jinja ? "enabled" : "disabled"),
|
||||
[](common_params & params) {
|
||||
params.use_jinja = true;
|
||||
{"--no-jinja"},
|
||||
string_format("whether to use jinja template engine for chat (default: %s)", params.use_jinja ? "enabled" : "disabled"),
|
||||
[](common_params & params, bool value) {
|
||||
params.use_jinja = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_MTMD}).set_env("LLAMA_ARG_JINJA"));
|
||||
add_opt(common_arg(
|
||||
{"--no-jinja"},
|
||||
string_format("disable jinja template for chat (default: %s)", params.use_jinja ? "disabled" : "enabled"),
|
||||
[](common_params & params) {
|
||||
params.use_jinja = false;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_MTMD}).set_env("LLAMA_ARG_NO_JINJA"));
|
||||
add_opt(common_arg(
|
||||
{"--reasoning-format"}, "FORMAT",
|
||||
"controls whether thought tags are allowed and/or extracted from the response, and in which format they're returned; one of:\n"
|
||||
|
|
@ -2673,15 +2716,16 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
}
|
||||
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_CHAT_TEMPLATE_FILE"));
|
||||
add_opt(common_arg(
|
||||
{"--prefill-assistant"},
|
||||
{"--no-prefill-assistant"},
|
||||
string_format(
|
||||
"whether to prefill the assistant's response if the last message is an assistant message (default: prefill enabled)\n"
|
||||
"when this flag is set, if the last message is an assistant message then it will be treated as a full message and not prefilled\n"
|
||||
),
|
||||
[](common_params & params) {
|
||||
params.prefill_assistant = false;
|
||||
[](common_params & params, bool value) {
|
||||
params.prefill_assistant = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_PREFILL_ASSISTANT"));
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_PREFILL_ASSISTANT"));
|
||||
add_opt(common_arg(
|
||||
{"-sps", "--slot-prompt-similarity"}, "SIMILARITY",
|
||||
string_format("how much the prompt of a request must match the prompt of a slot in order to use that slot (default: %.2f, 0.0 = disabled)\n", params.slot_prompt_similarity),
|
||||
|
|
|
|||
13
common/arg.h
13
common/arg.h
|
|
@ -16,6 +16,7 @@ struct common_arg {
|
|||
std::set<enum llama_example> examples = {LLAMA_EXAMPLE_COMMON};
|
||||
std::set<enum llama_example> excludes = {};
|
||||
std::vector<const char *> args;
|
||||
std::vector<const char *> args_neg; // for negated args like --no-xxx
|
||||
const char * value_hint = nullptr; // help text or example for arg value
|
||||
const char * value_hint_2 = nullptr; // for second arg value
|
||||
const char * env = nullptr;
|
||||
|
|
@ -25,6 +26,7 @@ struct common_arg {
|
|||
void (*handler_string) (common_params & params, const std::string &) = nullptr;
|
||||
void (*handler_str_str)(common_params & params, const std::string &, const std::string &) = nullptr;
|
||||
void (*handler_int) (common_params & params, int) = nullptr;
|
||||
void (*handler_bool) (common_params & params, bool) = nullptr;
|
||||
|
||||
common_arg() = default;
|
||||
|
||||
|
|
@ -48,6 +50,13 @@ struct common_arg {
|
|||
void (*handler)(common_params & params)
|
||||
) : args(args), help(help), handler_void(handler) {}
|
||||
|
||||
common_arg(
|
||||
const std::initializer_list<const char *> & args,
|
||||
const std::initializer_list<const char *> & args_neg,
|
||||
const std::string & help,
|
||||
void (*handler)(common_params & params, bool)
|
||||
) : args(args), args_neg(args_neg), help(help), handler_bool(handler) {}
|
||||
|
||||
// support 2 values for arg
|
||||
common_arg(
|
||||
const std::initializer_list<const char *> & args,
|
||||
|
|
@ -80,6 +89,10 @@ struct common_arg {
|
|||
}
|
||||
return strcmp(args[0], other.args[0]) == 0;
|
||||
}
|
||||
|
||||
// get all args and env vars (including negated args/env)
|
||||
std::vector<std::string> get_args() const;
|
||||
std::vector<std::string> get_env() const;
|
||||
};
|
||||
|
||||
namespace common_arg_utils {
|
||||
|
|
|
|||
|
|
@ -23,8 +23,14 @@ std::vector<std::string> common_preset::to_args() const {
|
|||
if (opt.value_hint == nullptr && opt.value_hint_2 == nullptr) {
|
||||
// flag option, no value
|
||||
if (common_arg_utils::is_falsey(value)) {
|
||||
// skip the flag
|
||||
args.pop_back();
|
||||
// use negative arg if available
|
||||
if (!opt.args_neg.empty()) {
|
||||
args.back() = opt.args_neg.back();
|
||||
} else {
|
||||
// otherwise, skip the flag
|
||||
// TODO: maybe throw an error instead?
|
||||
args.pop_back();
|
||||
}
|
||||
}
|
||||
}
|
||||
if (opt.value_hint != nullptr) {
|
||||
|
|
@ -141,10 +147,10 @@ static std::map<std::string, std::map<std::string, std::string>> parse_ini_from_
|
|||
static std::map<std::string, common_arg> get_map_key_opt(common_params_context & ctx_params) {
|
||||
std::map<std::string, common_arg> mapping;
|
||||
for (const auto & opt : ctx_params.options) {
|
||||
if (opt.env != nullptr) {
|
||||
mapping[opt.env] = opt;
|
||||
for (const auto & env : opt.get_env()) {
|
||||
mapping[env] = opt;
|
||||
}
|
||||
for (const auto & arg : opt.args) {
|
||||
for (const auto & arg : opt.get_args()) {
|
||||
mapping[rm_leading_dashes(arg)] = opt;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue