@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 1cb4ad8de9
Fork 0

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