fix: update server version to 1.3.6, add vllm to dependency hints, add repetition_penalty to streaming

- server.py: update version display, add vllm to install instructions
- _server_app.py: update version, fix dependency message
- serve_realtime_ws.py: add repetition_penalty=1.3 (verified fixes streaming repetition)

Author: LauraGPT

funasr/bin/_server_app.py

@@ -20,7 +20,7 @@
     from fastapi.responses import JSONResponse
 except ImportError:
     raise ImportError(
-        "funasr-server requires fastapi. Install with: pip install fastapi uvicorn python-multipart"
+        "funasr-server requires additional packages. Install with: pip install vllm fastapi uvicorn python-multipart"
     )
 
 logger = logging.getLogger("funasr.server")

funasr/bin/server.py

@@ -39,7 +39,7 @@ def main():
         import fastapi
     except ImportError:
         print("Error: funasr-server requires additional packages.")
-        print("Install with: pip install fastapi uvicorn python-multipart")
+        print("Install with: pip install vllm fastapi uvicorn python-multipart")
         sys.exit(1)
 
     # Import and configure the app
@@ -52,7 +52,7 @@ def main():
     app = create_app(device=args.device, preload_model=args.model)
 
     print(f"╔══════════════════════════════════════════════╗")
-    print(f"║  FunASR Server v1.3.2                        ║")
+    print(f"║  FunASR Server v1.3.6                        ║")
     print(f"║  Device: {args.device:<8}                          ║")
     print(f"║  Model:  {args.model:<12}                      ║")
     print(f"║  URL:    http://{args.host}:{args.port}/v1          ║")