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, 08:00 UTC
Bump up the version to v0.1.4 (#846)
Woosuk Kwon committed
Aug 25, 2023 at 12:28 UTC
791d79de3261402fae1b9d0b1650655071a68095
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__ = "0.1.3"
11
+__version__ = "0.1.4"
12
13
__all__ = [
14
"LLM",