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, 17:00 UTC
bump version to v0.6.1.post1 (#8440)
Simon Mo committed
Sep 12, 2024 at 21:39 UTC
acda0b35d00e733982aa4c1198f2bd381d368cb5
1 file changed
+2
-1
vllm/version.py
+2
-1
@@ -2,6 +2,7 @@ import warnings
2
3
try:
4
import vllm.commit_id
5
+
6
__commit__ = vllm.commit_id.__commit__
7
except Exception as e:
8
warnings.warn(f"Failed to read commit hash:\n{e}",
@@ -9,4 +10,4 @@ except Exception as e:
10
stacklevel=2)
11
__commit__ = "COMMIT_HASH_PLACEHOLDER"
12
12
-__version__ = "0.6.1"
13
+__version__ = "0.6.1.post1"