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/inference/core/__init__.py

@@ -1,10 +1,12 @@
 """Inference core: cache, executor, scheduler, task management."""
 
 from astrai.inference.core.cache import (
-    CacheView,
-    PagedCache,
+    Allocator,
+    KVCache,
+    KvcacheView,
     PagePool,
     PrefixCache,
+    Storage,
     TaskTable,
     page_hash,
 )
@@ -13,10 +15,12 @@ from astrai.inference.core.scheduler import InferenceScheduler
 from astrai.inference.core.task import STOP, Task, TaskManager, TaskStatus
 
 __all__ = [
-    "CacheView",
-    "PagedCache",
+    "Allocator",
+    "KVCache",
+    "KvcacheView",
     "PagePool",
     "PrefixCache",
+    "Storage",
     "TaskTable",
     "page_hash",
     "Executor",