[doc] updated inference readme (#5343)

colossalai/inference/kv_cache/block_cache.py

@@ -1,5 +1,7 @@
 from typing import Any
 
+__all__ = ["CacheBlock"]
+
 
 class CacheBlock:
     """A simplified version of logical cache block used for Paged Attention."""

colossalai/inference/kv_cache/kvcache_manager.py

@@ -10,6 +10,8 @@ from colossalai.utils import get_current_device
 
 from .block_cache import CacheBlock
 
+__all__ = ["KVCacheManager"]
+
 GIGABYTE = 1024**3