Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 17:25:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '12280ae9058600b0b14335fe59848e601e10eebc' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	common/CMakeLists.txt
#	docs/docker.md
#	examples/model-conversion/scripts/causal/compare-logits.py
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	tests/test-backend-ops.cpp
#	tests/test-barrier.cpp
#	tools/server/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2025-12-16 16:29:01 +08:00
parent 78bbe89956 12280ae905
commit e88bf41fdc
49 changed files with 1380 additions and 583 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+72 -14
View File
@@ -49,6 +49,7 @@
#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,
@@ -66,6 +67,15 @@ static std::string read_file(const std::string & fname) {
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;
@@ -136,7 +146,7 @@ static std::vector<std::string> break_str_into_lines(std::string input, size_t m
return result;
}
std::string common_arg::to_string() {
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
@@ -649,6 +659,53 @@ static void add_rpc_devices(const std::string & servers) {
}
}
bool common_params_parse(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;
}
}
// 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");
}
};
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()));
}
auto opt = *arg_to_options[arg];
std::string val;
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
@@ -694,25 +751,19 @@ static std::string list_builtin_chat_templates() {
return msg.str();
}
static bool is_truthy(const std::string & value) {
bool common_arg_utils::is_truthy(const std::string & value) {
return value == "on" || value == "enabled" || value == "1";
}
static bool is_falsey(const std::string & value) {
bool common_arg_utils::is_falsey(const std::string & value) {
return value == "off" || value == "disabled" || value == "0";
}
static bool is_autoy(const std::string & value) {
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 **)) {
// default values specific to example
// note: we place it here instead of inside server.cpp to allow llama-gen-docs to pick it up
if (ex == LLAMA_EXAMPLE_SERVER) {
params.use_jinja = true;
}
params.use_color = tty_can_use_colors();
// load dynamic backends
@@ -1807,7 +1858,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_CONT_BATCHING"));
add_opt(common_arg(
{"--mmproj"}, "FILE",
{"-mm", "--mmproj"}, "FILE",
"path to a multimodal projector file. see tools/mtmd/README.md\n"
"note: if -hf is used, this argument can be omitted",
[](common_params & params, const std::string & value) {
@@ -1815,7 +1866,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ"));
add_opt(common_arg(
{"--mmproj-url"}, "URL",
{"-mmu", "--mmproj-url"}, "URL",
"URL to a multimodal projector file. see tools/mtmd/README.md",
[](common_params & params, const std::string & value) {
params.mmproj.url = value;
@@ -2545,6 +2596,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.models_dir = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MODELS_DIR"));
add_opt(common_arg(
{"--models-preset"}, "PATH",
"path to INI file containing model presets for the router server (default: disabled)",
[](common_params & params, const std::string & value) {
params.models_preset = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MODELS_PRESET"));
add_opt(common_arg(
{"--models-max"}, "N",
string_format("for router server, maximum number of models to load simultaneously (default: %d, 0 = unlimited)", params.models_max),
@@ -2561,14 +2619,14 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_MODELS_AUTOLOAD"));
add_opt(common_arg(
{"--jinja"},
string_format("use jinja template for chat (default: %s)\n", params.use_jinja ? "enabled" : "disabled"),
string_format("use jinja template for chat (default: %s)", params.use_jinja ? "enabled" : "disabled"),
[](common_params & params) {
params.use_jinja = true;
}
).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)\n", params.use_jinja ? "enabled" : "disabled"),
string_format("disable jinja template for chat (default: %s)", params.use_jinja ? "disabled" : "enabled"),
[](common_params & params) {
params.use_jinja = false;
}
common/arg.h
+30 -2
View File
@@ -3,8 +3,10 @@
#include "common.h"
#include <set>
#include <map>
#include <string>
#include <vector>
#include <cstring>
//
// CLI argument parsing
@@ -24,6 +26,8 @@ struct common_arg {
void (*handler_str_str)(common_params & params, const std::string &, const std::string &) = nullptr;
void (*handler_int) (common_params & params, int) = nullptr;
common_arg() = default;
common_arg(
const std::initializer_list<const char *> & args,
const char * value_hint,
@@ -61,9 +65,29 @@ struct common_arg {
bool is_exclude(enum llama_example ex);
bool get_value_from_env(std::string & output) const;
bool has_value_from_env() const;
std::string to_string();
std::string to_string() const;
// for using as key in std::map
bool operator<(const common_arg& other) const {
if (args.empty() || other.args.empty()) {
return false;
}
return strcmp(args[0], other.args[0]) < 0;
}
bool operator==(const common_arg& other) const {
if (args.empty() || other.args.empty()) {
return false;
}
return strcmp(args[0], other.args[0]) == 0;
}
};
namespace common_arg_utils {
bool is_truthy(const std::string & value);
bool is_falsey(const std::string & value);
bool is_autoy(const std::string & value);
}
struct common_params_context {
enum llama_example ex = LLAMA_EXAMPLE_COMMON;
common_params & params;
@@ -76,7 +100,11 @@ struct common_params_context {
// if one argument has invalid value, it will automatically display usage of the specific argument (and not the full usage message)
bool common_params_parse(int argc, char ** argv, common_params & params, llama_example ex, void(*print_usage)(int, char **) = nullptr);
// function to be used by test-arg-parser
// parse input arguments from CLI into a map
// TODO: support repeated args in the future
bool common_params_parse(int argc, char ** argv, llama_example ex, std::map<common_arg, std::string> & out_map);
// initialize argument parser context - used by test-arg-parser and preset
common_params_context common_params_parser_init(common_params & params, llama_example ex, void(*print_usage)(int, char **) = nullptr);
struct common_remote_params {
common/common.h
+5 -4
View File
@@ -460,7 +460,7 @@ struct common_params {
std::string public_path = ""; // NOLINT
std::string api_prefix = ""; // NOLINT
std::string chat_template = ""; // NOLINT
bool use_jinja = false; // NOLINT
bool use_jinja = true; // NOLINT
bool enable_chat_template = true;
common_reasoning_format reasoning_format = COMMON_REASONING_FORMAT_DEEPSEEK;
int reasoning_budget = -1;
@@ -480,9 +480,10 @@ struct common_params {
bool endpoint_metrics = false;
// router server configs
std::string models_dir = ""; // directory containing models for the router server
int models_max = 4; // maximum number of models to load simultaneously
bool models_autoload = true; // automatically load models when requested via the router server
std::string models_dir = ""; // directory containing models for the router server
std::string models_preset = ""; // directory containing model presets for the router server
int models_max = 4; // maximum number of models to load simultaneously
bool models_autoload = true; // automatically load models when requested via the router server
bool log_json = false;
common/download.cpp
+69 -25
View File
@@ -12,6 +12,8 @@
#include <filesystem>
#include <fstream>
#include <future>
#include <map>
#include <mutex>
#include <regex>
#include <string>
#include <thread>
@@ -472,36 +474,79 @@ std::pair<long, std::vector<char>> common_remote_get_content(const std::string &
#elif defined(LLAMA_USE_HTTPLIB)
static bool is_output_a_tty() {
class ProgressBar {
static inline std::mutex mutex;
static inline std::map<const ProgressBar *, int> lines;
static inline int max_line = 0;
static void cleanup(const ProgressBar * line) {
lines.erase(line);
if (lines.empty()) {
max_line = 0;
}
}
static bool is_output_a_tty() {
#if defined(_WIN32)
return _isatty(_fileno(stdout));
return _isatty(_fileno(stdout));
#else
return isatty(1);
return isatty(1);
#endif
}
static void print_progress(size_t current, size_t total) {
if (!is_output_a_tty()) {
return;
}
if (!total) {
return;
public:
ProgressBar() = default;
~ProgressBar() {
std::lock_guard<std::mutex> lock(mutex);
cleanup(this);
}
size_t width = 50;
size_t pct = (100 * current) / total;
size_t pos = (width * current) / total;
void update(size_t current, size_t total) {
if (!is_output_a_tty()) {
return;
}
std::cout << "["
<< std::string(pos, '=')
<< (pos < width ? ">" : "")
<< std::string(width - pos, ' ')
<< "] " << std::setw(3) << pct << "% ("
<< current / (1024 * 1024) << " MB / "
<< total / (1024 * 1024) << " MB)\r";
std::cout.flush();
}
if (!total) {
return;
}
std::lock_guard<std::mutex> lock(mutex);
if (lines.find(this) == lines.end()) {
lines[this] = max_line++;
std::cout << "\n";
}
int lines_up = max_line - lines[this];
size_t width = 50;
size_t pct = (100 * current) / total;
size_t pos = (width * current) / total;
std::cout << "\033[s";
if (lines_up > 0) {
std::cout << "\033[" << lines_up << "A";
}
std::cout << "\033[2K\r["
<< std::string(pos, '=')
<< (pos < width ? ">" : "")
<< std::string(width - pos, ' ')
<< "] " << std::setw(3) << pct << "% ("
<< current / (1024 * 1024) << " MB / "
<< total / (1024 * 1024) << " MB) "
<< "\033[u";
std::cout.flush();
if (current == total) {
cleanup(this);
}
}
ProgressBar(const ProgressBar &) = delete;
ProgressBar & operator=(const ProgressBar &) = delete;
};
static bool common_pull_file(httplib::Client & cli,
const std::string & resolve_path,
@@ -523,6 +568,7 @@ static bool common_pull_file(httplib::Client & cli,
const char * func = __func__; // avoid __func__ inside a lambda
size_t downloaded = existing_size;
size_t progress_step = 0;
ProgressBar bar;
auto res = cli.Get(resolve_path, headers,
[&](const httplib::Response &response) {
@@ -554,7 +600,7 @@ static bool common_pull_file(httplib::Client & cli,
progress_step += len;
if (progress_step >= total_size / 1000 || downloaded == total_size) {
print_progress(downloaded, total_size);
bar.update(downloaded, total_size);
progress_step = 0;
}
return true;
@@ -562,8 +608,6 @@ static bool common_pull_file(httplib::Client & cli,
nullptr
);
std::cout << "\n";
if (!res) {
LOG_ERR("%s: error during download. Status: %d\n", __func__, res ? res->status : -1);
return false;
common/preset.cpp
+180
View File
@@ -0,0 +1,180 @@
#include "arg.h"
#include "preset.h"
#include "peg-parser.h"
#include "log.h"
#include <fstream>
#include <sstream>
#include <filesystem>
static std::string rm_leading_dashes(const std::string & str) {
size_t pos = 0;
while (pos < str.size() && str[pos] == '-') {
++pos;
}
return str.substr(pos);
}
std::vector<std::string> common_preset::to_args() const {
std::vector<std::string> args;
for (const auto & [opt, value] : options) {
args.push_back(opt.args.back()); // use the last arg as the main arg
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();
}
}
if (opt.value_hint != nullptr) {
// single value
args.push_back(value);
}
if (opt.value_hint != nullptr && opt.value_hint_2 != nullptr) {
throw std::runtime_error(string_format(
"common_preset::to_args(): option '%s' has two values, which is not supported yet",
opt.args.back()
));
}
}
return args;
}
std::string common_preset::to_ini() const {
std::ostringstream ss;
ss << "[" << name << "]\n";
for (const auto & [opt, value] : options) {
auto espaced_value = value;
string_replace_all(espaced_value, "\n", "\\\n");
ss << rm_leading_dashes(opt.args.back()) << " = ";
ss << espaced_value << "\n";
}
ss << "\n";
return ss.str();
}
static std::map<std::string, std::map<std::string, std::string>> parse_ini_from_file(const std::string & path) {
std::map<std::string, std::map<std::string, std::string>> parsed;
if (!std::filesystem::exists(path)) {
throw std::runtime_error("preset file does not exist: " + path);
}
std::ifstream file(path);
if (!file.good()) {
throw std::runtime_error("failed to open server preset file: " + path);
}
std::string contents((std::istreambuf_iterator<char>(file)), std::istreambuf_iterator<char>());
static const auto parser = build_peg_parser([](auto & p) {
// newline ::= "\r\n" / "\n" / "\r"
auto newline = p.rule("newline", p.literal("\r\n") | p.literal("\n") | p.literal("\r"));
// ws ::= [ \t]*
auto ws = p.rule("ws", p.chars("[ \t]", 0, -1));
// comment ::= [;#] (!newline .)*
auto comment = p.rule("comment", p.chars("[;#]", 1, 1) + p.zero_or_more(p.negate(newline) + p.any()));
// eol ::= ws comment? (newline / EOF)
auto eol = p.rule("eol", ws + p.optional(comment) + (newline | p.end()));
// ident ::= [a-zA-Z_] [a-zA-Z0-9_.-]*
auto ident = p.rule("ident", p.chars("[a-zA-Z_]", 1, 1) + p.chars("[a-zA-Z0-9_.-]", 0, -1));
// value ::= (!eol-start .)*
auto eol_start = p.rule("eol-start", ws + (p.chars("[;#]", 1, 1) | newline | p.end()));
auto value = p.rule("value", p.zero_or_more(p.negate(eol_start) + p.any()));
// header-line ::= "[" ws ident ws "]" eol
auto header_line = p.rule("header-line", "[" + ws + p.tag("section-name", p.chars("[^]]")) + ws + "]" + eol);
// kv-line ::= ident ws "=" ws value eol
auto kv_line = p.rule("kv-line", p.tag("key", ident) + ws + "=" + ws + p.tag("value", value) + eol);
// comment-line ::= ws comment (newline / EOF)
auto comment_line = p.rule("comment-line", ws + comment + (newline | p.end()));
// blank-line ::= ws (newline / EOF)
auto blank_line = p.rule("blank-line", ws + (newline | p.end()));
// line ::= header-line / kv-line / comment-line / blank-line
auto line = p.rule("line", header_line | kv_line | comment_line | blank_line);
// ini ::= line* EOF
auto ini = p.rule("ini", p.zero_or_more(line) + p.end());
return ini;
});
common_peg_parse_context ctx(contents);
const auto result = parser.parse(ctx);
if (!result.success()) {
throw std::runtime_error("failed to parse server config file: " + path);
}
std::string current_section = COMMON_PRESET_DEFAULT_NAME;
std::string current_key;
ctx.ast.visit(result, [&](const auto & node) {
if (node.tag == "section-name") {
const std::string section = std::string(node.text);
current_section = section;
parsed[current_section] = {};
} else if (node.tag == "key") {
const std::string key = std::string(node.text);
current_key = key;
} else if (node.tag == "value" && !current_key.empty() && !current_section.empty()) {
parsed[current_section][current_key] = std::string(node.text);
current_key.clear();
}
});
return parsed;
}
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 & arg : opt.args) {
mapping[rm_leading_dashes(arg)] = opt;
}
}
return mapping;
}
common_presets common_presets_load(const std::string & path, common_params_context & ctx_params) {
common_presets out;
auto key_to_opt = get_map_key_opt(ctx_params);
auto ini_data = parse_ini_from_file(path);
for (auto section : ini_data) {
common_preset preset;
if (section.first.empty()) {
preset.name = COMMON_PRESET_DEFAULT_NAME;
} else {
preset.name = section.first;
}
LOG_DBG("loading preset: %s\n", preset.name.c_str());
for (const auto & [key, value] : section.second) {
LOG_DBG("option: %s = %s\n", key.c_str(), value.c_str());
if (key_to_opt.find(key) != key_to_opt.end()) {
preset.options[key_to_opt[key]] = value;
LOG_DBG("accepted option: %s = %s\n", key.c_str(), value.c_str());
} else {
// TODO: maybe warn about unknown key?
}
}
out[preset.name] = preset;
}
return out;
}
common/preset.h
+32
View File
@@ -0,0 +1,32 @@
#pragma once
#include "common.h"
#include "arg.h"
#include <string>
#include <vector>
#include <map>
//
// INI preset parser and writer
//
constexpr const char * COMMON_PRESET_DEFAULT_NAME = "default";
struct common_preset {
std::string name;
// TODO: support repeated args in the future
std::map<common_arg, std::string> options;
// convert preset to CLI argument list
std::vector<std::string> to_args() const;
// convert preset to INI format string
std::string to_ini() const;
// TODO: maybe implement to_env() if needed
};
// interface for multiple presets in one file
using common_presets = std::map<std::string, common_preset>;
common_presets common_presets_load(const std::string & path, common_params_context & ctx_params);