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
e40fa136aad5fde3d77e43e21b078e972be743fd
1 file changed
+1
-1
cacheflow/block.py
+1
-1
@@ -7,7 +7,7 @@ BLANK_TOKEN_ID = -1
7
8
class LogicalTokenBlock:
9
10
- def __int__(
10
+ def __init__(
11
self,
12
block_number: int,
13
block_size: int,