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 16, 18:15 UTC
Bump version to v0.5.5 (#7823)
Simon Mo committed
Aug 23, 2024 at 11:35 UTC
09c7792610ada9f88bbf87d32b472dd44bf23cc2
1 file changed
+1
-1
vllm/version.py
+1
-1
@@ -9,4 +9,4 @@ except Exception as e:
9
stacklevel=2)
10
__commit__ = "COMMIT_HASH_PLACEHOLDER"
11
12
-__version__ = "0.5.4"
12
+__version__ = "0.5.5"