Higher priority for user input of max_prefill_tokens & format (#540)

python/sglang/srt/models/gemma.py

@@ -6,7 +6,7 @@ from typing import Iterable, Optional, Tuple
 import torch
 from torch import nn
 from transformers import PretrainedConfig
-from vllm.config import LoRAConfig, CacheConfig
+from vllm.config import CacheConfig, LoRAConfig
 from vllm.distributed import get_tensor_model_parallel_world_size
 from vllm.model_executor.layers.activation import GeluAndMul
 from vllm.model_executor.layers.layernorm import RMSNorm