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

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

python/sglang/srt/models/mixtral.py

@@ -23,7 +23,6 @@ from torch import nn
 from transformers import MixtralConfig
 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.fused_moe_triton import FusedMoE
 from sglang.srt.layers.layernorm import RMSNorm
@@ -42,6 +41,7 @@ from sglang.srt.layers.vocab_parallel_embedding import (
 )
 from sglang.srt.managers.schedule_batch import global_server_args_dict
 from sglang.srt.model_executor.forward_batch_info import ForwardBatch
+from sglang.srt.model_loader.weight_utils import default_weight_loader
 
 
 class MixtralMoE(nn.Module):
@@ -291,7 +291,6 @@ class MixtralForCausalLM(nn.Module):
         self,
         config: MixtralConfig,
         quant_config: Optional[QuantizationConfig] = None,
-        cache_config=None,
     ) -> None:
         super().__init__()
         self.config = config