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, 06:45 UTC
Bump up the version to v0.2.0 (#1212)
Woosuk Kwon committed
Sep 28, 2023 at 15:30 UTC
e2fb71ec9f2c3168ba8614408fa807a5f65707c5
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__ = "0.1.7"
11
+__version__ = "0.2.0"
12
13
__all__ = [
14
"LLM",