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 to v0.4.0 (#3705)
Simon Mo committed
Mar 28, 2024 at 18:26 UTC
27a57cad52f2688fca024322b751a54f52b5e84f
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__ = "0.3.3"
11
+__version__ = "0.4.0"
12
13
__all__ = [
14
"LLM",