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 17, 09:15 UTC
Fix typo
Woosuk Kwon committed
Feb 14, 2023 at 01:19 UTC
c574f1950642ea835ede31d5458975ab4bc6e80f
1 file changed
+1
-1
cacheflow/utils.py
+1
-1
@@ -11,7 +11,7 @@ class Counter:
11
def __init__(self, start: int = 0) -> None:
12
self.counter = start
13
14
- def next(self) -> int:
14
+ def __next__(self) -> int:
15
id = self.counter
16
self.counter += 1
17
return id