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 0.5.3.post1 (#6696)
Simon Mo committed
Jul 23, 2024 at 10:08 UTC
38c4b7e863570a045308af814c72f4504297222e
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__ = "0.5.3"
12
+__version__ = "0.5.3.post1"