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, 06:45 UTC
[FIX] Fix formatting error
Zhuohan Li committed
Nov 29, 2023 at 00:40 UTC
1cb4ad8de98b672873dbfc1f246fbceae29234a5
1 file changed
-1
vllm/core/block_manager.py
-1
@@ -6,7 +6,6 @@ from vllm.block import PhysicalTokenBlock
6
from vllm.sequence import Sequence, SequenceGroup, SequenceStatus
7
from vllm.utils import Device
8
9
-
9
# Mapping: logical block number -> physical block.
10
BlockTable = List[PhysicalTokenBlock]
11