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 v0.1.5 (#944)
Woosuk Kwon committed
Sep 8, 2023 at 08:15 UTC
852ef5b4f5481ce526c804ea234d1de0df91f48d
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__ = "0.1.4"
11
+__version__ = "0.1.5"
12
13
__all__ = [
14
"LLM",