EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Release v0.4.5.post2 (#5582)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-04-20 14:12:37 -07:00
committed by GitHub
parent b54b5a96e4
commit fbdc94ba59
5 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docker/Dockerfile.rocm
View File

@@ -1,5 +1,5 @@
# Usage (to build SGLang ROCm docker image): # Usage (to build SGLang ROCm docker image):
# docker build --build-arg SGL_BRANCH=v0.4.5.post1 -t v0.4.5.post1-rocm630 -f Dockerfile.rocm . # docker build --build-arg SGL_BRANCH=v0.4.5.post2 -t v0.4.5.post2-rocm630 -f Dockerfile.rocm .
# default base image # default base image
ARG BASE_IMAGE="rocm/sgl-dev:vllm20250114" ARG BASE_IMAGE="rocm/sgl-dev:vllm20250114"

4
docs/developer/setup_github_runner.md
View File

@@ -11,9 +11,9 @@ docker pull nvidia/cuda:12.1.1-devel-ubuntu22.04
# Nvidia # Nvidia
docker run --shm-size 128g -it -v /tmp/huggingface:/hf_home --gpus all nvidia/cuda:12.1.1-devel-ubuntu22.04 /bin/bash docker run --shm-size 128g -it -v /tmp/huggingface:/hf_home --gpus all nvidia/cuda:12.1.1-devel-ubuntu22.04 /bin/bash
# AMD # AMD
docker run --rm --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.4.5.post1-rocm630 /bin/bash docker run --rm --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.4.5.post2-rocm630 /bin/bash
# AMD just the last 2 GPUs # AMD just the last 2 GPUs
docker run --rm --device=/dev/kfd --device=/dev/dri/renderD176 --device=/dev/dri/renderD184 --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.4.5.post1-rocm630 /bin/bash docker run --rm --device=/dev/kfd --device=/dev/dri/renderD176 --device=/dev/dri/renderD184 --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.4.5.post2-rocm630 /bin/bash
``` ```
### Step 2: Configure the runner by `config.sh` ### Step 2: Configure the runner by `config.sh`

12
docs/start/install.md
View File

@@ -11,7 +11,7 @@ It is recommended to use uv to install the dependencies for faster installation:
```bash ```bash
pip install --upgrade pip pip install --upgrade pip
pip install uv pip install uv
uv pip install "sglang[all]>=0.4.5.post1" uv pip install "sglang[all]>=0.4.5.post2"
``` ```
**Quick Fixes to Common Problems** **Quick Fixes to Common Problems**
@@ -29,7 +29,7 @@ uv pip install "sglang[all]>=0.4.5.post1"
```bash ```bash
# Use the last release branch # Use the last release branch
git clone -b v0.4.5.post1 https://github.com/sgl-project/sglang.git git clone -b v0.4.5.post2 https://github.com/sgl-project/sglang.git
cd sglang cd sglang
pip install --upgrade pip pip install --upgrade pip
@@ -44,7 +44,7 @@ Note: For AMD ROCm system with Instinct/MI GPUs, do following instead:
```bash ```bash
# Use the last release branch # Use the last release branch
git clone -b v0.4.5.post1 https://github.com/sgl-project/sglang.git git clone -b v0.4.5.post2 https://github.com/sgl-project/sglang.git
cd sglang cd sglang
pip install --upgrade pip pip install --upgrade pip
@@ -73,7 +73,7 @@ docker run --gpus all \
Note: For AMD ROCm system with Instinct/MI GPUs, it is recommended to use `docker/Dockerfile.rocm` to build images, example and usage as below: Note: For AMD ROCm system with Instinct/MI GPUs, it is recommended to use `docker/Dockerfile.rocm` to build images, example and usage as below:
```bash ```bash
docker build --build-arg SGL_BRANCH=v0.4.5.post1 -t v0.4.5.post1-rocm630 -f Dockerfile.rocm . docker build --build-arg SGL_BRANCH=v0.4.5.post2 -t v0.4.5.post2-rocm630 -f Dockerfile.rocm .
alias drun='docker run -it --rm --network=host --device=/dev/kfd --device=/dev/dri --ipc=host \ alias drun='docker run -it --rm --network=host --device=/dev/kfd --device=/dev/dri --ipc=host \
--shm-size 16G --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \ --shm-size 16G --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \
@@ -82,11 +82,11 @@ alias drun='docker run -it --rm --network=host --device=/dev/kfd --device=/dev/d
drun -p 30000:30000 \ drun -p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \ -v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \ --env "HF_TOKEN=<secret>" \
v0.4.5.post1-rocm630 \ v0.4.5.post2-rocm630 \
python3 -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --host 0.0.0.0 --port 30000 python3 -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct --host 0.0.0.0 --port 30000
# Till flashinfer backend available, --attention-backend triton --sampling-backend pytorch are set by default # Till flashinfer backend available, --attention-backend triton --sampling-backend pytorch are set by default
drun v0.4.5.post1-rocm630 python3 -m sglang.bench_one_batch --batch-size 32 --input 1024 --output 128 --model amd/Meta-Llama-3.1-8B-Instruct-FP8-KV --tp 8 --quantization fp8 drun v0.4.5.post2-rocm630 python3 -m sglang.bench_one_batch --batch-size 32 --input 1024 --output 128 --model amd/Meta-Llama-3.1-8B-Instruct-FP8-KV --tp 8 --quantization fp8
``` ```
## Method 4: Using docker compose ## Method 4: Using docker compose

2
python/pyproject.toml
View File

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
[project] [project]
name = "sglang" name = "sglang"
version = "0.4.5.post1" version = "0.4.5.post2"
description = "SGLang is yet another fast serving framework for large language models and vision language models." description = "SGLang is yet another fast serving framework for large language models and vision language models."
readme = "README.md" readme = "README.md"
requires-python = ">=3.8" requires-python = ">=3.8"

2
python/sglang/version.py
View File

@@ -1 +1 @@
__version__ = "0.4.5.post1" __version__ = "0.4.5.post2"