feat: update other MoE models deps (#2156)

python/sglang/srt/models/mixtral.py

@@ -22,7 +22,6 @@ import torch
 from torch import nn
 from transformers import MixtralConfig
 from vllm.distributed import get_tensor_model_parallel_world_size
-from vllm.model_executor.layers.fused_moe import FusedMoE
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader
 
@@ -36,6 +35,7 @@ from sglang.srt.layers.logits_processor import LogitsProcessor
 from sglang.srt.layers.quantization.base_config import QuantizationConfig
 from sglang.srt.layers.radix_attention import RadixAttention
 from sglang.srt.layers.torchao_utils import apply_torchao_config_
+from sglang.srt.layers.triton_fused_moe import FusedMoE
 from sglang.srt.layers.vocab_parallel_embedding import (
     ParallelLMHead,
     VocabParallelEmbedding,