organize

services/llama-cpp.nix

@@ -1,46 +0,0 @@
-{
-  pkgs,
-  service_configs,
-  config,
-  inputs,
-  lib,
-  ...
-}:
-{
-  services.llama-cpp = {
-    enable = false;
-    model = toString (
-      pkgs.fetchurl {
-        url = "https://huggingface.co/unsloth/Qwen3.5-9B-GGUF/resolve/main/Qwen3.5-9B-Q4_K_M.gguf";
-        sha256 = "03b74727a860a56338e042c4420bb3f04b2fec5734175f4cb9fa853daf52b7e8";
-      }
-    );
-    port = service_configs.ports.private.llama_cpp.port;
-    host = "0.0.0.0";
-    package = (lib.optimizePackage inputs.llamacpp.packages.${pkgs.system}.default);
-    extraFlags = [
-      # "-ngl"
-      # "12"
-      "-c"
-      "32768"
-      "-ctk"
-      "q8_0"
-      "-ctv"
-      "turbo4"
-      "-fa"
-      "on"
-      "--api-key-file"
-      config.age.secrets.llama-cpp-api-key.path
-    ];
-  };
-
-  # have to do this in order to get vulkan to work
-  systemd.services.llama-cpp.serviceConfig.DynamicUser = lib.mkForce false;
-
-  # Auth handled by llama-cpp --api-key-file (Bearer token).
-  # No caddy_auth — the API key is the auth layer, and caddy_auth's basic
-  # auth would block Bearer-only clients like oh-my-pi.
-  services.caddy.virtualHosts."llm.${service_configs.https.domain}".extraConfig = ''
-    reverse_proxy :${toString config.services.llama-cpp.port}
-  '';
-}