Merge pull request #359 from janhq/update-dev-from-master-2025-12-12-00-38

Sync master with upstream release b7360

Author: jan-service-account

.github/workflows/build.yml

@@ -1770,7 +1770,7 @@ jobs:
           echo "Fetch llama2c model"
           wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories260K/stories260K.bin
           ./bin/llama-convert-llama2c-to-ggml --copy-vocab-from-model ./tok512.bin --llama2c-model stories260K.bin --llama2c-output-model stories260K.gguf
-          ./bin/llama-cli -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
+          ./bin/llama-completion -m stories260K.gguf -p "One day, Lily met a Shoggoth" -n 500 -c 256
 
   ubuntu-cmake-sanitizer-riscv64-native:
     runs-on: RISCV64

common/CMakeLists.txt

@@ -73,6 +73,8 @@ add_library(${TARGET} STATIC
     ngram-cache.h
     peg-parser.cpp
     peg-parser.h
+    preset.cpp
+    preset.h
     regex-partial.cpp
     regex-partial.h
     sampling.cpp

common/arg.cpp

@@ -47,6 +47,7 @@
 #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,
@@ -64,6 +65,15 @@ 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;
@@ -134,7 +144,7 @@ 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
@@ -647,6 +657,53 @@ 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
@@ -692,25 +749,19 @@ 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
@@ -2543,6 +2594,13 @@ 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),
@@ -2559,14 +2617,14 @@ 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

@@ -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

@@ -464,7 +464,7 @@ 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;
@@ -484,9 +484,10 @@ 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;