Update app.py

app.py

@@ -4,6 +4,7 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 import gradio as gr
+import spaces
 from transformers import (
     AutoTokenizer,
     PretrainedConfig,
@@ -247,6 +248,7 @@ def load_model():
 
 model, tokenizer, load_status = load_model()
 
+@spaces.GPU
 @torch.no_grad()
 def generate_reply_stream(ids: list[int], max_new_tokens=150, temperature=0.8, top_k=50):
     """Autoregressive generation with ROSA updates, yielding token lists and comprehensive throughput metrics."""