Update handler.py

handler.py

@@ -5,7 +5,7 @@ import torch
 class EndpointHandler:
     def __init__(self, path=""):
         self.tokenizer =AutoTokenizer.from_pretrained(path)
-        self.model = AutoModelForCausalLM.from_pretrained(path, device_map='auto')
+        self.model = AutoModelForCausalLM.from_pretrained(path, device_map='cuda')
             
     def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
         sys_prompt=data["prompt"]