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 17, 04:15 UTC
Bump up version to v0.3.2 (#2968)
This version is for more model support. Add support for Gemma models (#2964) and OLMo models (#2832).
Zhuohan Li committed
Feb 21, 2024 at 11:47 UTC
8fbd84bf7839d53e6dd26a1dd4473dd1a99aab6e
1 file changed
+1
-1
vllm/__init__.py
+1
-1
@@ -8,7 +8,7 @@ from vllm.entrypoints.llm import LLM
8
from vllm.outputs import CompletionOutput, RequestOutput
9
from vllm.sampling_params import SamplingParams
10
11
-__version__ = "0.3.1"
11
+__version__ = "0.3.2"
12
13
__all__ = [
14
"LLM",