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, 01:45 UTC
bump version to v0.4.2 (#4600)
Simon Mo committed
May 4, 2024 at 17:09 UTC
8d8357c8ed1f3ddb6a0e8f3287ec669a13d77df1
2 files changed
+2
-2
.github/workflows/scripts/create_release.js
+1
-1
@@ -8,7 +8,7 @@ module.exports = async (github, context, core) => {
8
generate_release_notes: true,
9
name: process.env.RELEASE_TAG,
10
owner: context.repo.owner,
11
- prerelease: false,
11
+ prerelease: true,
12
repo: context.repo.repo,
13
tag_name: process.env.RELEASE_TAG,
14
});
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__ = "0.4.1"
12
+__version__ = "0.4.2"
13
14
__all__ = [
15
"LLM",