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, 03:00 UTC
Bump version of 0.4.1 (#4177)
Simon Mo committed
Apr 19, 2024 at 01:00 UTC
221d93ecbf51102df69deaf153d35df6d93370f6
1 file changed
+1
-1
vllm/__init__.py
+1
-1
@@ -9,7 +9,7 @@ from vllm.model_executor.models import ModelRegistry
9
from vllm.outputs import CompletionOutput, RequestOutput
10
from vllm.sampling_params import SamplingParams
11
12
-__version__ = "0.4.0.post1"
12
+__version__ = "0.4.1"
13
14
__all__ = [
15
"LLM",