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
Minor
Woosuk Kwon committed
Feb 14, 2023 at 09:06 UTC
c80ed212a19ae124e6e926ead1ee17200fc91646
1 file changed
+1
-1
cacheflow/master/block_manager.py
+1
-1
@@ -1,4 +1,4 @@
1
-from typing import Dict, Iterable, List, Optional, Set, Tuple
1
+from typing import Dict, List, Optional, Set, Tuple
2
3
from cacheflow.block import PhysicalTokenBlock
4
from cacheflow.sequence import Sequence