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, 00:30 UTC
Bump version to v0.4.3 (#5046)
Simon Mo committed
May 30, 2024 at 13:13 UTC
87a658c81219568fc30081d9cc11327238160563
1 file changed
+1
-1
vllm/__init__.py
+1
-1
@@ -12,7 +12,7 @@ from vllm.outputs import (CompletionOutput, EmbeddingOutput,
12
from vllm.pooling_params import PoolingParams
13
from vllm.sampling_params import SamplingParams
14
15
-__version__ = "0.4.2"
15
+__version__ = "0.4.3"
16
17
__all__ = [
18
"LLM",