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 16, 23:15 UTC
Bump version to v0.5.0 (#5384)
Simon Mo committed
Jun 10, 2024 at 17:56 UTC
114332b88e499f03a5af6fa9fc3633492352af52
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__ = "0.4.3"
15
+__version__ = "0.5.0"
16
17
__all__ = [
18
"LLM",