A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 23:45 UTC
[v1][Core] Clean up usages of `SpecializedManager` (#21407)
Signed-off-by: Zhou Fang <fang.github@gmail.com>
Zhou Fang committed
Jul 24, 2025 at 00:40 UTC
fc5f756db4ce3d0cc5b1c495bd70a4b5601cffe2
2 files changed
+1
-1
tests/v1/core/test_single_type_kv_cache_manager.py
renamed
vllm/v1/core/single_type_kv_cache_manager.py
+1
-1
@@ -27,7 +27,7 @@ class SingleTypeKVCacheManager(ABC):
27
caching_hash_fn: Callable,
28
) -> None:
29
"""
30
- Initializes the SpecializedManager.
30
+ Initializes the SingleTypeKVCacheManager.
31
Args:
32
kv_cache_spec: The kv_cache_spec for this manager.
33
block_pool: The block pool.