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, 05:30 UTC
[Easy] Get rid of unnecessary paraenthesis in kv_cache_manager (#26842)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Jialin Ouyang committed
Oct 15, 2025 at 02:17 UTC
7f83b4ee8ea4577f1c4b32e547b6917b9c6e2d3d
1 file changed
+1
-1
vllm/v1/core/kv_cache_manager.py
+1
-1
@@ -219,7 +219,7 @@ class KVCacheManager:
219
self.prefix_cache_stats.queries += request.num_tokens
220
self.prefix_cache_stats.hits += num_new_computed_tokens
221
222
- return (self.create_kv_cache_blocks(computed_blocks), num_new_computed_tokens)
222
+ return self.create_kv_cache_blocks(computed_blocks), num_new_computed_tokens
223
224
def allocate_slots(
225
self,