Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
-from vllm import LLMEngine, SamplingParams
+from vllm import SamplingParams, LLM
 
 # Load the model and tokenizer from Hugging Face
 model_name = "Qwen/Qwen2-7B"  
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-engine = LLMEngine(model=model_name)
+engine = LLM.from_pretrained(model_name)
 
 def generate_response(prompt, max_tokens, temperature, top_p):
     # Tokenize the prompt