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 v0.2.1 (#1355)
Zhuohan Li committed
Oct 16, 2023 at 12:58 UTC
651c614aa43e497a2e2aab473493ba295201ab20
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__ = "0.2.0"
11
+__version__ = "0.2.1"
12
13
__all__ = [
14
"LLM",