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 v0.1.6 (#989)
Zhuohan Li committed
Sep 8, 2023 at 00:07 UTC
1117aa1411d9858ea5eef8a81e044379432e6d0e
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__ = "0.1.5"
11
+__version__ = "0.1.6"
12
13
__all__ = [
14
"LLM",