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 to v0.3.3 (#3129)
Woosuk Kwon committed
Mar 1, 2024 at 12:58 UTC
82091b864af105dbe373353655dc9d8c0a6ba66f
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__ = "0.3.2"
11
+__version__ = "0.3.3"
12
13
__all__ = [
14
"LLM",