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 13, 2023 at 18:51 UTC
531e1c74e81075de85070dae84938e597756684b
1 file changed
+1
-1
cacheflow/master/scheduler.py
+1
-1
@@ -8,7 +8,7 @@ from cacheflow.sequence import SequenceStatus
8
9
class Scheduler:
10
11
- def __int__(
11
+ def __init__(
12
self,
13
controllers: List,
14
block_size: int,