feat: BaseModelConfig + DeepSeekMoE + 工厂模式替代 if/else

- BaseModelConfig: fields() 精确字段匹配 + 类型矫正 + 未知key警告
- DeepSeekMoE: 共享专家 + 路由专家 + top-K 门控
- AttnFactory/FFNFactory: 装饰器注册，DecoderBlock 零分支
- config 用 attn_type/ffn_type 驱动组件选择

astrai/model/components/decoder_block.py

@@ -4,8 +4,8 @@ import torch.nn as nn
 from torch import Tensor
 
 from astrai.inference.core.cache import KvcacheView
-from astrai.model.components.attention import GQA
-from astrai.model.components.mlp import MLP
+from astrai.model.components.attention import AttnFactory
+from astrai.model.components.mlp import FFNFactory
 from astrai.model.components.norm import RMSNorm
 
 
@@ -20,20 +20,24 @@ class DecoderBlock(nn.Module):
         use_qk_norm: bool,
         use_gated_attention: bool,
         layer_id: int,
+        attn_type: str = "gqa",
+        ffn_type: str = "mlp",
+        **moe_kwargs,
     ):
         super().__init__()
-        self.attention = GQA(
-            dim,
-            n_heads,
-            n_kv_heads,
-            use_qk_norm,
-            norm_eps,
-            use_gated_attention,
-            layer_id,
+        self.attention = AttnFactory.create(
+            attn_type,
+            dim=dim,
+            n_heads=n_heads,
+            n_kv_heads=n_kv_heads,
+            use_qk_norm=use_qk_norm,
+            norm_eps=norm_eps,
+            use_gated_attention=use_gated_attention,
+            layer_id=layer_id,
         )
         self.input_norm = RMSNorm(dim, norm_eps)
-        self.mlp = MLP(dim, dim_ffn)
         self.post_attention_norm = RMSNorm(dim, norm_eps)
+        self.mlp = FFNFactory.create(ffn_type, dim, dim_ffn, **moe_kwargs)
 
     def forward(
         self,