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, 20:45 UTC
bump version to v0.5.2 (#6433)
Simon Mo committed
Jul 15, 2024 at 10:27 UTC
64fdc08c72f1ba923d7a4f76858fcad3551282a5
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__ = "0.5.1"
12
+__version__ = "0.5.2"