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, 05:30 UTC
Bump up to v0.2.4 (#2034)
Woosuk Kwon committed
Dec 11, 2023 at 11:49 UTC
4dd4b5c538dabcf2c822bc91b4f760364520e5af
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__ = "0.2.3"
11
+__version__ = "0.2.4"
12
13
__all__ = [
14
"LLM",