Update inference.py

inference.py

@@ -5,8 +5,19 @@ import sys
 import torch
 from typing import List, Dict
 
-# Ensure vllm is installed and specify version to match CUDA compatibility
-import vllm
+# Function to install vllm if not already installed
+def install_vllm():
+    try:
+        import vllm
+    except ImportError:
+        subprocess.check_call([
+            sys.executable, "-m", "pip", "install",
+            "vllm @ https://github.com/vllm-project/vllm/releases/download/v0.6.1.post1/vllm-0.6.1.post1+cu118-cp310-cp310-manylinux1_x86_64.whl"
+        ])
+        import vllm
+
+# Call the function to install vllm
+install_vllm()
 
 # Import the necessary modules after installation
 from vllm import LLM, SamplingParams