refactor: 重构 cache 和 inference 参数体系，分离存储与分配

- 合并 GenerationRequest/GenerationParams，统一 max_tokens 参数名
- PagePool/PrefixCache 分离为 Allocator + PrefixCache + PagePool
- 拆分 KV 存储为独立 Storage 类，PagedCache → KVCache，CacheView → KvcacheView
- Allocator.inc_ref 移除 LRU 防止竞争，Storage.write 增加负页防御
- Allocator/PrefixCache/TaskTable 加 threading.Lock 保证线程安全
- server.py uvicorn.run 改为传 app 对象修复导入错误
- benchmark.py 适配 KVCache 新 API

astrai/model/module.py

@@ -5,7 +5,7 @@ import torch.nn as nn
 import torch.nn.functional as F
 from torch import Tensor
 
-from astrai.inference.core.cache import CacheView
+from astrai.inference.core.cache import KvcacheView
 
 
 def repeat_kv(x: Tensor, n_rep: int) -> Tensor:
@@ -147,7 +147,7 @@ class GQA(nn.Module):
         x: Tensor,
         rotary_emb: Tensor,
         attn_mask: Tensor = None,
-        paged_cache: Optional[CacheView] = None,
+        paged_cache: Optional[KvcacheView] = None,
     ) -> Tensor:
         is_causal = attn_mask is None
 
@@ -227,7 +227,7 @@ class MLA(nn.Module):
         x: Tensor,
         rotary_emb: Tensor,
         attn_mask: Tensor = None,
-        paged_cache: Optional[CacheView] = None,
+        paged_cache: Optional[KvcacheView] = None,
     ) -> Tensor:
         bsz, seq_len, _ = x.size()
         is_causal = attn_mask is None
@@ -306,7 +306,7 @@ class DecoderBlock(nn.Module):
         x: Tensor,
         rotary_emb: Tensor,
         attention_mask: Optional[Tensor] = None,
-        paged_cache: Optional[CacheView] = None,
+        paged_cache: Optional[KvcacheView] = None,
     ) -> Tensor:
         attn_output = self.attention(
             self.input_norm(x),

astrai/model/transformer.py

@@ -5,7 +5,7 @@ import torch.nn as nn
 from torch import Tensor
 
 from astrai.config.model_config import ModelConfig
-from astrai.inference.core.cache import CacheView
+from astrai.inference.core.cache import KvcacheView
 from astrai.model.automodel import AutoModel
 from astrai.model.module import (
     DecoderBlock,
@@ -122,7 +122,7 @@ class Transformer(AutoModel):
         self,
         input_ids: Tensor,
         input_mask: Optional[Tensor] = None,
-        paged_cache: Optional[CacheView] = None,
+        paged_cache: Optional[KvcacheView] = None,
         position_ids: Optional[Tensor] = None,
     ) -> Tensor:
         assert input_ids.ndim == 2