Exploring the GPUs inside the funciton

app.py

@@ -1,19 +1,31 @@
 import spaces
 import gradio as gr
+import torch
 
 
 
 # Use a pipeline as a high-level helper
 from transformers import pipeline
-pipe = pipeline("text-generation", model="NousResearch/Hermes-3-Llama-3.1-8B", max_new_tokens=200)
+# pipe = pipeline("text-generation", model="NousResearch/Hermes-3-Llama-3.1-8B", max_new_tokens=200, device=0)
 
-@spaces.GPU(duration=120)
+@spaces.GPU
 def llama3_1_8B(question):
     messages = [
     {"role": "user", "content": question},
     ]
-    responses = pipe(messages)
-    return str(responses)
+    # responses = pipe(messages)
+    if torch.cuda.is_available():
+        num_devices = torch.cuda.device_count()
+        print(f"Number of CUDA devices: {num_devices}")
+        
+        for i in range(num_devices):
+            print(f"Device {i}: {torch.cuda.get_device_name(i)}")
+                    
+    else:
+        print("CUDA is not available.")
+
+
+    return "Hi"
 
 def greet(name):
     return "Hello " + name + "!!???"