NVIDIA Dynamo源码编译

Ref

https://github.com/PyO3/maturin

Rust 程序设计语言

代码库：

https://github.com/ai-dynamo/dynamo

https://github.com/ai-dynamo/nixl

dynamo/container/Dockerfile.vllm

构建ai_dynamo

Install uv: uv

curl -LsSf https://astral.sh/uv/install.sh | sh

在顶层目录：

uv build --wheel --out-dir /workspace/dist

构建ai_dynamo_runtime

参考https://github.com/ai-dynamo/dynamo/tree/main/lib/bindings/python

下载rust环境：

国内服务器最好设置环境变量，否则rustup-init.sh运行时的下载极其慢：

export RUSTUP_DIST_SERVER='https://mirrors.ustc.edu.cn/rust-static'
export RUSTUP_UPDATE_ROOT='https://mirrors.ustc.edu.cn/rust-static/rustup'

# curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
wget https://static.rust-lang.org/rustup/rustup-init.sh
./rustup-init.sh

安装依赖：

这里假设你已经有一个Python conda环境，否则可以安装miniconda设置环境，或者按照推荐使用uv环境。

pip install maturin
apt install protobuf-compiler

下载源码：

git clone --recursive https://github.com/ai-dynamo/dynamo.git
git clone --recursive https://github.com/ai-dynamo/nixl.git

在目录dynamo/lib/bindings/python运行

maturin build

即可在target/wheels/生成whl包。

或者：

uv build --wheel --out-dir /workspace/dist

构建nixl

依赖安装

sudo apt install -y build-essential cmake pkg-config
pip install meson ninja pybind11

在nixl源码目录执行(路径根据你的需求修改)：

INSTALL_DIR=/root/nixl
UCX_INSTALL_DIR=/root/ucx./util/build.sh $INSTALL_DIR $UCX_INSTALL_DIR

或者参考readme.md和util/build.sh分别构建ucx和nixl

首先构建ucx

wget https://github.com/openucx/ucx/releases/download/v1.18.0/ucx-1.18.0.tar.gz
tar xzf ucx-1.18.0.tar.gz
cd ucx-1.18.0
./contrib/configure-release --prefix=/root/ucx
make -j8
make install

构建nixl wheel包

在nixl源码路径，设置编译好的ucx路径

ref https://mesonbuild.com/meson-python/how-to-guides/meson-args.html

python -m pip wheel --config-settings=setup-args="-Ducx_path=/root/ucx" .
# or 
pip install build
python -m build -Csetup-args="-Ducx_path=/root/ucx" .

或者：

uv build --wheel --out-dir /workspace/dist

构建ai_dynamo_vllm

下载VLLM 0.7.2的分支，然后打patch dynamo\container\deps\vllm\vllm_v0.7.2-dynamo-kv-disagg-patch.patch，然后源码编译VLLM。

相当于直接编译VLLM，参考vllm doc和其他博客

Installation — vLLM

https://github.com/vllm-project/vllm/blob/main/.github/workflows/scripts/build.sh

https://zhuanlan.zhihu.com/p/692200573

# for cuda12.1, pytorch 2.5.1
# v0.0.28.post3 build for PyTorch 2.5.1
pip3 install -U xformers==v0.0.28.post3 --index-url https://download.pytorch.org/whl/cu121

git clone --recursive -b v0.7.2 https://github.com/vllm-project/vllm.git
git apply dynamo/container/deps/vllm/vllm_v0.7.2-dynamo-kv-disagg-patch.patchpython setup.py bdist_wheel