Add device arg to model_args passed to LLM object in VLLM model class (#2879)

* fix: pass device arg in model_ar in vllm_causallms

* casting device arg to str in vLLM model args

lm_eval/models/vllm_causallms.py

@@ -100,6 +100,7 @@ class VLLM(TemplateLM):
             "swap_space": int(swap_space),
             "quantization": quantization,
             "seed": int(seed),
+            "device": str(device),
         }
         self.model_args.update(kwargs)
         self.batch_size = (