cont

Author: ngxson

common/arg.cpp

@@ -2600,6 +2600,13 @@ 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),

common/common.h

@@ -482,9 +482,10 @@ 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/preset.cpp

@@ -54,12 +54,12 @@ static std::map<std::string, std::map<std::string, std::string>> parse_ini_from_
     std::map<std::string, std::map<std::string, std::string>> parsed;
 
     if (!std::filesystem::exists(path)) {
-        return parsed; // return empty if file does not exist (expected behavior)
+        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 config file: " + path);
+        throw std::runtime_error("failed to open server preset file: " + path);
     }
 
     std::string contents((std::istreambuf_iterator<char>(file)), std::istreambuf_iterator<char>());

tools/server/server-models.cpp

@@ -138,10 +138,9 @@ static std::vector<local_model> list_local_models(const std::string & dir) {
 //
 
 
-server_presets::server_presets(int argc, char ** argv, common_params & base_params, const std::string & models_dir)
+server_presets::server_presets(int argc, char ** argv, common_params & base_params, const std::string & presets_path)
         : ctx_params(common_params_parser_init(base_params, LLAMA_EXAMPLE_SERVER)) {
-    if (!models_dir.empty()) {
-        auto presets_path = models_dir + DIRECTORY_SEPARATOR + "presets.ini";
+    if (!presets_path.empty()) {
         presets = common_presets_load(presets_path, ctx_params);
         SRV_INF("Loaded %zu presets from %s\n", presets.size(), presets_path.c_str());
     }
@@ -167,6 +166,14 @@ server_presets::server_presets(int argc, char ** argv, common_params & base_para
             control_args[env] = opt;
         }
     }
+
+    // remove any router-controlled args from base_args
+    for (const auto & cargs : control_args) {
+        auto it = base_args.find(cargs.second);
+        if (it != base_args.end()) {
+            base_args.erase(it);
+        }
+    }
 }
 
 common_preset server_presets::get_preset(const std::string & name) {
@@ -209,7 +216,7 @@ server_models::server_models(
         const common_params & params,
         int argc,
         char ** argv,
-        char ** envp) : base_params(params), presets(argc, argv, base_params, params.models_dir) {
+        char ** envp) : base_params(params), presets(argc, argv, base_params, params.models_preset) {
     for (int i = 0; i < argc; i++) {
         base_args.push_back(std::string(argv[i]));
     }