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, 05:30 UTC
Bump up to v0.2.6 (#2157)
Woosuk Kwon committed
Dec 17, 2023 at 10:34 UTC
671af2b1c0b3ed6d856d37c21a561cc429a10701
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__ = "0.2.5"
11
+__version__ = "0.2.6"
12
13
__all__ = [
14
"LLM",