Unverified Commit b0d25e72 authored by Yineng Zhang's avatar Yineng Zhang Committed by GitHub
Browse files

chore: bump v0.5.2 (#10221)

parent a2424068
name: Release Docker Images
name: Release Docker Xeon Images
on:
push:
branches:
......
......@@ -14,13 +14,15 @@ jobs:
environment: 'prod'
strategy:
matrix:
cuda_version: ['12.6.1', '12.8.1']
cuda_version: ['12.6.1', '12.8.1', '12.9.1']
build_type: ['all', 'blackwell']
exclude:
- cuda_version: '12.6.1'
build_type: 'blackwell'
- cuda_version: '12.8.1'
build_type: 'all'
- cuda_version: '12.9.1'
build_type: 'all'
steps:
- name: Delete huge unnecessary tools folder
run: rm -rf /opt/hostedtoolcache
......@@ -61,6 +63,8 @@ jobs:
cuda_tag="cu126"
elif [ "${{ matrix.cuda_version }}" = "12.8.1" ]; then
cuda_tag="cu128"
elif [ "${{ matrix.cuda_version }}" = "12.9.1" ]; then
cuda_tag="cu129"
else
echo "Unsupported CUDA version"
exit 1
......@@ -86,3 +90,8 @@ jobs:
docker tag lmsysorg/sglang:${tag}${tag_suffix} lmsysorg/sglang:latest${tag_suffix}
docker push lmsysorg/sglang:latest${tag_suffix}
fi
if [ "${{ matrix.cuda_version }}" = "12.9.1" ]; then
docker tag lmsysorg/sglang:${tag}${tag_suffix} lmsysorg/sglang:v${version}
docker push lmsysorg/sglang:v${version}
fi
......@@ -33,7 +33,7 @@ Add [performance optimization options](#performance-optimization-options) as nee
```bash
# Installation
pip install "sglang[all]>=0.5.2rc2"
pip install "sglang[all]>=0.5.2"
# Launch
python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-V3 --tp 8 --trust-remote-code
......
ARG CUDA_VERSION=12.6.1
ARG CUDA_VERSION=12.9.1
FROM nvidia/cuda:${CUDA_VERSION}-cudnn-devel-ubuntu22.04 as base
ARG BUILD_TYPE=all
......
# Usage (to build SGLang ROCm docker image):
# docker build --build-arg SGL_BRANCH=v0.5.2rc2 --build-arg GPU_ARCH=gfx942 -t v0.5.2rc2-rocm630-mi30x -f Dockerfile.rocm .
# docker build --build-arg SGL_BRANCH=v0.5.2rc2 --build-arg GPU_ARCH=gfx942-rocm700 -t v0.5.2rc2-rocm700-mi30x -f Dockerfile.rocm .
# docker build --build-arg SGL_BRANCH=v0.5.2rc2 --build-arg GPU_ARCH=gfx950 -t v0.5.2rc2-rocm700-mi35x -f Dockerfile.rocm .
# docker build --build-arg SGL_BRANCH=v0.5.2 --build-arg GPU_ARCH=gfx942 -t v0.5.2-rocm630-mi30x -f Dockerfile.rocm .
# docker build --build-arg SGL_BRANCH=v0.5.2 --build-arg GPU_ARCH=gfx942-rocm700 -t v0.5.2-rocm700-mi30x -f Dockerfile.rocm .
# docker build --build-arg SGL_BRANCH=v0.5.2 --build-arg GPU_ARCH=gfx950 -t v0.5.2-rocm700-mi35x -f Dockerfile.rocm .
# Default base images
......
......@@ -12,7 +12,7 @@ It is recommended to use uv for faster installation:
```bash
pip install --upgrade pip
pip install uv
uv pip install "sglang[all]>=0.5.2rc2"
uv pip install "sglang[all]>=0.5.2"
```
**Quick fixes to common problems**
......@@ -24,7 +24,7 @@ uv pip install "sglang[all]>=0.5.2rc2"
```bash
# Use the last release branch
git clone -b v0.5.2rc2 https://github.com/sgl-project/sglang.git
git clone -b v0.5.2 https://github.com/sgl-project/sglang.git
cd sglang
# Install the python packages
......
......@@ -44,7 +44,7 @@ You can install SGLang using one of the methods below.
```bash
# Use the last release branch
git clone -b v0.5.2rc2 https://github.com/sgl-project/sglang.git
git clone -b v0.5.2 https://github.com/sgl-project/sglang.git
cd sglang
# Compile sgl-kernel
......
......@@ -99,7 +99,7 @@ We are also providing a DeepEP-compatible Library as a drop-in replacement of de
```shell
# Use the last release branch
git clone -b v0.5.2rc2 https://github.com/sgl-project/sglang.git
git clone -b v0.5.2 https://github.com/sgl-project/sglang.git
cd sglang
pip install --upgrade pip
......
......@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
[project]
name = "sglang"
version = "0.5.2rc2"
description = "SGLang is yet another fast serving framework for large language models and vision language models."
version = "0.5.2"
description = "SGLang is a fast serving framework for large language models and vision language models."
readme = "README.md"
requires-python = ">=3.10"
license = { file = "LICENSE" }
......
__version__ = "0.5.2rc2"
__version__ = "0.5.2"
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment