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, 22:00 UTC
bump version to v0.5.1 (#6157)
Simon Mo committed
Jul 5, 2024 at 12:04 UTC
abad5746a71dc87fb2b1d43cae645dcda79b64a2
1 file changed
+1
-1
vllm/version.py
+1
-1
@@ -1 +1 @@
1
-__version__ = "0.5.0.post1"
1
+__version__ = "0.5.1"