From 023288645b80fb41b3eed55fd413dd69a7904593 Mon Sep 17 00:00:00 2001 From: Yineng Zhang Date: Thu, 31 Jul 2025 05:50:17 -0700 Subject: [PATCH] chore: bump v0.4.10 (#8608) --- benchmark/deepseek_v3/README.md | 2 +- docs/references/setup_github_runner.md | 4 ++-- docs/start/install.md | 12 ++++++------ python/pyproject.toml | 2 +- python/sglang/version.py | 2 +- 5 files changed, 11 insertions(+), 11 deletions(-) diff --git a/benchmark/deepseek_v3/README.md b/benchmark/deepseek_v3/README.md index f8efab2c1..6e1aad03c 100644 --- a/benchmark/deepseek_v3/README.md +++ b/benchmark/deepseek_v3/README.md @@ -33,7 +33,7 @@ Add [performance optimization options](#performance-optimization-options) as nee ```bash # Installation -pip install "sglang[all]>=0.4.9.post6" +pip install "sglang[all]>=0.4.10" # Launch python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-V3 --tp 8 --trust-remote-code diff --git a/docs/references/setup_github_runner.md b/docs/references/setup_github_runner.md index 43ae73ac5..a259d63fc 100644 --- a/docs/references/setup_github_runner.md +++ b/docs/references/setup_github_runner.md @@ -11,9 +11,9 @@ docker pull nvidia/cuda:12.1.1-devel-ubuntu22.04 # Nvidia docker run --shm-size 128g -it -v /tmp/huggingface:/hf_home --gpus all nvidia/cuda:12.1.1-devel-ubuntu22.04 /bin/bash # AMD -docker run --rm --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.4.9.post6-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:v0.4.10-rocm630 /bin/bash # 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:v0.4.9.post6-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:v0.4.10-rocm630 /bin/bash ``` ### Step 2: Configure the runner by `config.sh` diff --git a/docs/start/install.md b/docs/start/install.md index 288fd3da9..47886197d 100644 --- a/docs/start/install.md +++ b/docs/start/install.md @@ -11,7 +11,7 @@ It is recommended to use uv to install the dependencies for faster installation: ```bash pip install --upgrade pip pip install uv -uv pip install "sglang[all]>=0.4.9.post6" +uv pip install "sglang[all]>=0.4.10" ``` **Quick Fixes to Common Problems** @@ -27,7 +27,7 @@ uv pip install "sglang[all]>=0.4.9.post6" ```bash # Use the last release branch -git clone -b v0.4.9.post6 https://github.com/sgl-project/sglang.git +git clone -b v0.4.10 https://github.com/sgl-project/sglang.git cd sglang pip install --upgrade pip @@ -42,7 +42,7 @@ Note: For AMD ROCm system with Instinct/MI GPUs, do following instead: ```bash # Use the last release branch -git clone -b v0.4.9.post6 https://github.com/sgl-project/sglang.git +git clone -b v0.4.10 https://github.com/sgl-project/sglang.git cd sglang pip install --upgrade pip @@ -74,7 +74,7 @@ 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: ```bash -docker build --build-arg SGL_BRANCH=v0.4.9.post6 -t v0.4.9.post6-rocm630 -f Dockerfile.rocm . +docker build --build-arg SGL_BRANCH=v0.4.10 -t v0.4.10-rocm630 -f Dockerfile.rocm . 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 \ @@ -83,11 +83,11 @@ alias drun='docker run -it --rm --network=host --device=/dev/kfd --device=/dev/d drun -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=" \ - v0.4.9.post6-rocm630 \ + v0.4.10-rocm630 \ 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 -drun v0.4.9.post6-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 v0.4.10-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 ``` Note: Please refer to [the CPU installation guide using Docker](../references/cpu.md#install-using-docker) diff --git a/python/pyproject.toml b/python/pyproject.toml index ca0c92cbf..f3fcb1b7f 100644 --- a/python/pyproject.toml +++ b/python/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "sglang" -version = "0.4.9.post6" +version = "0.4.10" description = "SGLang is yet another fast serving framework for large language models and vision language models." readme = "README.md" requires-python = ">=3.8" diff --git a/python/sglang/version.py b/python/sglang/version.py index 6cf0091fa..805e7c470 100644 --- a/python/sglang/version.py +++ b/python/sglang/version.py @@ -1 +1 @@ -__version__ = "0.4.9.post6" +__version__ = "0.4.10"