Update app.py

app.py

@@ -11,9 +11,9 @@ print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 # client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-client = InferenceClient("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B")
-
+client = InferenceClient("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B").to('cuda')
 
+@spaces.GPU
 def respond(
     message,
     history: list[tuple[str, str]],