fix: include RPC devices in --list-devices (#2182)

examples/common/common.cpp

@@ -596,6 +596,11 @@ ArgOptions SDContextParams::get_options() {
     };
 
     options.bool_options = {
+        {"",
+         "--list-devices",
+         "list available ggml backend devices, including --rpc-servers (one 'name<TAB>description' per line), and exit; "
+         "the names are the device names accepted by --backend and --params-backend",
+         true, &list_devices},
         {"",
          "--disable-prefetch",
          "disable asynchronous next-segment weight prefetch (defaults to false)",
@@ -819,23 +824,22 @@ ArgOptions SDContextParams::get_options() {
          "but it usually offers faster inference speed and, in some cases, lower memory usage. "
          "The at_runtime mode, on the other hand, is exactly the opposite.",
          on_lora_apply_mode_arg},
-        {"",
-         "--list-devices",
-         "list available ggml backend devices (one 'name<TAB>description' per line) and exit; "
-         "the names are the device names accepted by --backend and --params-backend",
-         [](int /*argc*/, const char** /*argv*/, int /*index*/) {
-             size_t device_list_size = sd_list_devices(nullptr, 0);
-             std::vector<char> devices(device_list_size + 1);
-             sd_list_devices(devices.data(), devices.size());
-             fputs(devices.data(), stdout);
-             std::exit(0);
-             return 0;
-         }},
     };
 
     return options;
 }
 
+bool SDContextParams::print_devices() const {
+    if (!sd_add_rpc_servers(rpc_servers.c_str())) {
+        return false;
+    }
+    size_t device_list_size = sd_list_devices(nullptr, 0);
+    std::vector<char> devices(device_list_size + 1);
+    sd_list_devices(devices.data(), devices.size());
+    fputs(devices.data(), stdout);
+    return true;
+}
+
 void SDContextParams::build_embedding_map() {
     static const std::vector<std::string> valid_ext = {".gguf", ".safetensors", ".pt", ".ckpt"};