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 v0.6.0 (#8166)
Simon Mo committed
Sep 4, 2024 at 16:34 UTC
32e7db25365415841ebc7c4215851743fbb1bad1
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__ = "0.5.5"
12
+__version__ = "0.6.0"