Update app.py

app.py

@@ -2,6 +2,14 @@ import gradio as gr
 from llama_cpp import Llama
 import time
 
+zero = torch.Tensor([0]).cuda()
+print(zero.device)
+
+@spaces.GPU
+def greet(n):
+	print(zero.device)
+	return f"Hello {zero + n} Tensor"
+
 # Load your LLaMA model with GPU support, quantization, and multi-threading
 llm = Llama.from_pretrained(
     repo_id="Ahil1991/Bee-8.3B",