fix bug

handler.py

@@ -12,10 +12,10 @@ class EndpointHandler:
             "Qwen/Qwen2-1.5B-Instruct",
             torch_dtype=torch.float16 if device == "cuda" else torch.float32,
             device_map="auto"
-        ).to(device)
+        )
         
-        # create inference pipeline
-        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0 if device == "cuda" else -1)
+        # create inference pipeline without specifying the device
+        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
         inputs = data.pop("inputs", data)