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, 23:15 UTC
bump version to v0.5.0.post1 (#5522)
Simon Mo committed
Jun 13, 2024 at 21:42 UTC
0f0d8bc065f3608e7657a9696f5d2d7c0d6722d1
1 file changed
+1
-1
vllm/version.py
+1
-1
@@ -1 +1 @@
1
-__version__ = "0.5.0"
1
+__version__ = "0.5.0.post1"