fixed a lot of things and actually got it to work

wyoming_glados/__main__.py

@@ -24,6 +24,10 @@ async def main() -> None:
                         help="Directory containing model files (config.json, *.safetensors, style_vectors.npy)")
     parser.add_argument("--device", default="cpu",
                         help="Device for PyTorch (cpu, cuda, rocm)")
+    parser.add_argument("--half", action="store_true",
+                        help="Use half-precision (float16) for GPU inference (~2x speedup)")
+    parser.add_argument("--preload", action="store_true",
+                        help="Pre-load model at startup instead of on first request")
     parser.add_argument("--debug", action="store_true",
                         help="Log DEBUG messages")
     parser.add_argument("--version", action="version",
@@ -78,6 +82,8 @@ async def main() -> None:
     _LOGGER.info("Starting GLaDOS Wyoming TTS server on %s", args.uri)
     _LOGGER.info("Model directory: %s", model_dir)
     _LOGGER.info("Device: %s", device)
+    _LOGGER.info("Half precision: %s", args.half)
+    _LOGGER.info("Preload model: %s", args.preload)
 
     server_task = asyncio.create_task(
         server.run(
@@ -86,6 +92,8 @@ async def main() -> None:
                 wyoming_info,
                 model_dir,
                 device,
+                half=args.half,
+                preload=args.preload,
             )
         )
     )