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

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

python/sglang/srt/models/olmoe.py

@@ -34,8 +34,6 @@ from vllm.model_executor.layers.linear import (
     RowParallelLinear,
 )
 from vllm.model_executor.layers.rotary_embedding import get_rope
-from vllm.model_executor.model_loader.weight_utils import default_weight_loader
-from vllm.utils import print_warning_once
 
 from sglang.srt.layers.activation import SiluAndMul
 from sglang.srt.layers.fused_moe_triton import FusedMoE
@@ -48,7 +46,8 @@ from sglang.srt.layers.vocab_parallel_embedding import (
     VocabParallelEmbedding,
 )
 from sglang.srt.model_executor.forward_batch_info import ForwardBatch
-from sglang.srt.utils import make_layers
+from sglang.srt.model_loader.weight_utils import default_weight_loader
+from sglang.srt.utils import make_layers, print_warning_once
 
 
 class OlmoeMoE(nn.Module):
@@ -300,7 +299,6 @@ class OlmoeForCausalLM(nn.Module):
     def __init__(
         self,
         config: PretrainedConfig,
-        cache_config=None,
         quant_config: Optional[QuantizationConfig] = None,
     ) -> None:
         super().__init__()