Feature(MInference): add zeroGPU

app.py

@@ -73,7 +73,7 @@ if torch.cuda.is_available() and _is_package_available("pycuda"):
 terminators = [tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>")]
 
 
-# @spaces.GPU(duration=120)
+@spaces.GPU(duration=120)
 def chat_llama3_8b(
     message: str, history: list, temperature: float, max_new_tokens: int
 ) -> str: