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 version to 0.1.1 (#204)
Zhuohan Li committed
Jun 22, 2023 at 15:33 UTC
83658c8ace771617460f9e2d5f1cf6f811d6d6fb
1 file changed
+1
-1
vllm/__init__.py
+1
-1
@@ -6,7 +6,7 @@ from vllm.entrypoints.llm import LLM
6
from vllm.outputs import CompletionOutput, RequestOutput
7
from vllm.sampling_params import SamplingParams
8
9
-__version__ = "0.1.0"
9
+__version__ = "0.1.1"
10
11
__all__ = [
12
"LLM",