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.post2 (#8473)
Simon Mo committed
Sep 13, 2024 at 11:35 UTC
9ba0817ff1eb514f51cc6de9cb8e16c98d6ee44f
1 file changed
+1
-1
vllm/version.py
+1
-1
@@ -10,4 +10,4 @@ except Exception as e:
10
stacklevel=2)
11
__commit__ = "COMMIT_HASH_PLACEHOLDER"
12
13
-__version__ = "0.6.1.post1"
13
+__version__ = "0.6.1.post2"