Update model_loader deps and qqq quantization deps (#2220) (#2318)

Co-authored-by: HandH1998 <1335248067@qq.com>

python/sglang/srt/models/gemma.py

@@ -21,10 +21,8 @@ from typing import Iterable, Optional, Tuple
 import torch
 from torch import nn
 from transformers import PretrainedConfig
-from vllm.config import LoRAConfig
 from vllm.distributed import get_tensor_model_parallel_world_size
 from vllm.model_executor.layers.rotary_embedding import get_rope
-from vllm.model_executor.model_loader.weight_utils import default_weight_loader
 
 from sglang.srt.layers.activation import GeluAndMul
 from sglang.srt.layers.layernorm import RMSNorm
@@ -38,6 +36,7 @@ from sglang.srt.layers.quantization.base_config import QuantizationConfig
 from sglang.srt.layers.radix_attention import RadixAttention
 from sglang.srt.layers.vocab_parallel_embedding import VocabParallelEmbedding
 from sglang.srt.model_executor.forward_batch_info import ForwardBatch
+from sglang.srt.model_loader.weight_utils import default_weight_loader
 
 
 class GemmaMLP(nn.Module):
@@ -278,10 +277,7 @@ class GemmaForCausalLM(nn.Module):
         self,
         config: PretrainedConfig,
         quant_config: Optional[QuantizationConfig] = None,
-        lora_config: Optional[LoRAConfig] = None,
-        cache_config=None,
     ) -> None:
-        del lora_config  # Unused.
         super().__init__()
         self.config = config
         self.quant_config = quant_config