add install.sh

app.py

@@ -2,6 +2,34 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStream
 from threading import Thread
 import gradio as gr
 import json
+import subprocess
+import os
+
+
+def install_vllm_from_patch():
+    script_path = "./install.sh"
+    if not os.path.exists(script_path):
+        print(f"Error: install.sh is not exist!")
+        return False
+
+    try:
+        result = subprocess.run(
+            ["bash", script_path],
+            check=True,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            text = True,
+            timeout = 500
+        )
+        print(f"result: {result}")
+        return True
+    except Exception as e:
+        print(f"Error: {str(e)}")
+        return False
+
+#install vllm from patch file
+install_vllm_from_patch()
+
 
 # load model and tokenizer
 model_name = "inclusionAI/Ling-mini-2.0"