Dockerfile.sglang

# SPDX-FileCopyrightText: Copyright (c) 2024-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

ARG BASE_IMAGE="nvcr.io/nvidia/cuda-dl-base"
# FIXME: NCCL will hang with 25.03, so use 25.01 for now
# Please check https://github.com/ai-dynamo/dynamo/pull/1065
# for details and reproducer to manually test if the image
# can be updated to later versions.
ARG BASE_IMAGE_TAG="25.01-cuda12.8-devel-ubuntu24.04"
ARG RELEASE_BUILD
ARG RUNTIME_IMAGE="nvcr.io/nvidia/cuda"
ARG RUNTIME_IMAGE_TAG="12.8.1-runtime-ubuntu24.04"

# Define general architecture ARGs for supporting both x86 and aarch64 builds.
#   ARCH: Used for package suffixes (e.g., amd64, arm64)
#   ARCH_ALT: Used for Rust targets, manylinux suffix (e.g., x86_64, aarch64)
#
# Default values are for x86/amd64:
#   --build-arg ARCH=amd64 --build-arg ARCH_ALT=x86_64
#
# For arm64/aarch64, build with:
#   --build-arg ARCH=arm64 --build-arg ARCH_ALT=aarch64
#
# NOTE: There isn't an easy way to define one of these values based on the other value
# without adding if statements everywhere, so just define both as ARGs for now.
ARG ARCH=amd64
ARG ARCH_ALT=x86_64

ARG SGLANG_VERSION="0.4.9.post1"
ARG SGL_KERNEL_VERSION="0.2.4"

FROM ${BASE_IMAGE}:${BASE_IMAGE_TAG} AS nixl_base

# Redeclare ARCH and ARCH_ALT so they're available in this stage
ARG ARCH
ARG ARCH_ALT

WORKDIR /opt/nixl
# Add a cache hint that only changes when the nixl commit changes
ARG NIXL_COMMIT
# This line acts as a cache key - it only changes when NIXL_COMMIT changes
RUN echo "NIXL commit: ${NIXL_COMMIT}" > /opt/nixl/commit.txt
# Copy the nixl source
COPY --from=nixl . .

##################################
########## Base Image ############
##################################

FROM ${BASE_IMAGE}:${BASE_IMAGE_TAG} AS base

# Redeclare ARCH and ARCH_ALT so they're available in this stage
ARG ARCH
ARG ARCH_ALT

USER root
ARG PYTHON_VERSION=3.12

RUN apt-get update -y && \
    apt-get install -y \
    # NIXL build dependencies
    cmake \
    meson \
    ninja-build \
    pybind11-dev \
    # Rust build dependencies
	clang \
    libclang-dev \
	git \
    # Install utilities
    nvtop \
    tmux \
    vim \
    autoconf \
    libtool \
    net-tools

WORKDIR /workspace

### UCX EFA Setup ###
RUN rm -rf /opt/hpcx/ucx
RUN rm -rf /usr/local/ucx
RUN cd /usr/local/src && \
    git clone https://github.com/openucx/ucx.git && \
    cd ucx &&                   \
    git checkout v1.19.x &&     \
    ./autogen.sh && ./configure \
    --prefix=/usr/local/ucx     \
    --enable-shared             \
    --disable-static            \
    --disable-doxygen-doc       \
    --enable-optimizations      \
    --enable-cma                \
    --enable-devel-headers      \
    --with-cuda=/usr/local/cuda \
    --with-verbs                \
    --with-efa                  \
    --with-dm                   \
    --with-gdrcopy=/usr/local   \
    --enable-mt &&              \
    make -j &&                  \
    make -j install-strip &&    \
    ldconfig

ENV LD_LIBRARY_PATH=/usr/lib:/usr/local/ucx/lib:$LD_LIBRARY_PATH
ENV CPATH=/usr/include:$CPATH
ENV PATH=/usr/bin:$PATH
ENV PKG_CONFIG_PATH=/usr/lib/pkgconfig:$PKG_CONFIG_PATH
SHELL ["/bin/bash", "-c"]

WORKDIR /workspace

### NIXL SETUP ###
# Copy nixl source, and use commit hash as cache hint
COPY --from=nixl_base /opt/nixl /opt/nixl
COPY --from=nixl_base /opt/nixl/commit.txt /opt/nixl/commit.txt
RUN if [ "$ARCH" = "arm64" ]; then \
        cd /opt/nixl && \
        mkdir build && \
        meson setup build/ --prefix=/usr/local/nixl -Dgds_path=/usr/local/cuda/targets/sbsa-linux && \
        cd build/ && \
        ninja && \
        ninja install; \
    else \
        cd /opt/nixl && \
        mkdir build && \
        meson setup build/ --prefix=/usr/local/nixl && \
        cd build/ && \
        ninja && \
        ninja install; \
    fi

### NATS & ETCD SETUP ###
# nats
RUN wget --tries=3 --waitretry=5 https://github.com/nats-io/nats-server/releases/download/v2.10.28/nats-server-v2.10.28-${ARCH}.deb && \
    dpkg -i nats-server-v2.10.28-${ARCH}.deb && rm nats-server-v2.10.28-${ARCH}.deb
# etcd
ENV ETCD_VERSION="v3.5.21"
RUN wget --tries=3 --waitretry=5 https://github.com/etcd-io/etcd/releases/download/$ETCD_VERSION/etcd-$ETCD_VERSION-linux-${ARCH}.tar.gz -O /tmp/etcd.tar.gz && \
    mkdir -p /usr/local/bin/etcd && \
    tar -xvf /tmp/etcd.tar.gz -C /usr/local/bin/etcd --strip-components=1 && \
    rm /tmp/etcd.tar.gz
ENV PATH=/usr/local/bin/etcd/:$PATH


### VIRTUAL ENVIRONMENT SETUP ###

# Install uv and create virtualenv
COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
RUN mkdir /opt/dynamo && \
    uv venv /opt/dynamo/venv --python 3.12

# Activate virtual environment
ENV VIRTUAL_ENV=/opt/dynamo/venv
ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"

# Install NIXL Python module
RUN cd /opt/nixl && uv build . --out-dir /workspace/wheels/nixl

# Install the wheel
# TODO: Move NIXL wheel install to the wheel_builder stage
RUN uv pip install /workspace/wheels/nixl/*.whl

# Install sglang
#TODO: Built wheel should become an artifact which can be cached and reused in subsequent builds
ARG SGLANG_VERSION
RUN --mount=type=cache,target=/root/.cache/uv \
    cd /opt && \
    git clone https://github.com/sgl-project/sglang.git && \
    cd sglang && \
    git checkout v${SGLANG_VERSION} && \
    # Install in editable mode for development
    uv pip install -e "python[all]"

# Set env var that allows for forceful shutdown of inflight requests in SGL's TokenizerManager
ENV SGL_FORCE_SHUTDOWN=1

# Common dependencies
RUN --mount=type=bind,source=./container/deps/requirements.txt,target=/tmp/requirements.txt \
    uv pip install --requirement /tmp/requirements.txt

# Install test dependencies
RUN --mount=type=bind,source=./container/deps/requirements.test.txt,target=/tmp/requirements.txt \
    uv pip install --requirement /tmp/requirements.txt

# ### MISC UTILITY SETUP ###

# Finish pyright install
RUN pyright --help > /dev/null 2>&1

# Enable Git operations in the /workspace directory
RUN printf "[safe]\n      directory=/workspace\n" > /root/.gitconfig


### BUILDS ###

# Rust build/dev dependencies
RUN apt update -y && \
    apt install --no-install-recommends -y \
    build-essential \
    protobuf-compiler \
    cmake \
    libssl-dev \
    pkg-config

ENV RUSTUP_HOME=/usr/local/rustup \
    CARGO_HOME=/usr/local/cargo \
    PATH=/usr/local/cargo/bin:$PATH \
    RUST_VERSION=1.87.0

# Define Rust target based on ARCH_ALT ARG
ARG RUSTARCH=${ARCH_ALT}-unknown-linux-gnu

# Install Rust using RUSTARCH derived from ARCH_ALT
RUN wget --tries=3 --waitretry=5 "https://static.rust-lang.org/rustup/archive/1.28.1/${RUSTARCH}/rustup-init" && \
    # TODO: Add SHA check back based on RUSTARCH
    chmod +x rustup-init && \
    ./rustup-init -y --no-modify-path --profile minimal --default-toolchain $RUST_VERSION --default-host ${RUSTARCH} && \
    rm rustup-init && \
    chmod -R a+w $RUSTUP_HOME $CARGO_HOME

ARG CARGO_BUILD_JOBS
# Set CARGO_BUILD_JOBS to 16 if not provided
# This is to prevent cargo from building $(nproc) jobs in parallel,
# which might exceed the number of opened files limit.
ENV CARGO_BUILD_JOBS=${CARGO_BUILD_JOBS:-16}

#######################################
########## Local Development ##########
#######################################

FROM base AS local-dev

# https://code.visualstudio.com/remote/advancedcontainers/add-nonroot-user
# Will use the default ubuntu user, but give sudo access
# Needed so files permissions aren't set to root ownership when writing from inside container

# Don't want ubuntu to be editable, just change uid and gid. User ubuntu is hardcoded in .devcontainer
ENV USERNAME=ubuntu
ARG USER_UID=1000
ARG USER_GID=1000

RUN apt-get update && apt-get install -y sudo gnupg2 gnupg1 \
    && echo "$USERNAME ALL=(root) NOPASSWD:ALL" > /etc/sudoers.d/$USERNAME \
    && chmod 0440 /etc/sudoers.d/$USERNAME \
    && mkdir -p /home/$USERNAME \
    && chown -R $USERNAME:$USERNAME /home/$USERNAME \
    && rm -rf /var/lib/apt/lists/* \
    && chsh -s /bin/bash $USERNAME

# This is a slow operation (~40s on my cpu)
# Much better than chown -R $USERNAME:$USERNAME /opt/dynamo/venv (~10min on my cpu)
COPY --from=base --chown=$USER_UID:$USER_GID /opt/dynamo/venv/ /opt/dynamo/venv/
RUN chown $USERNAME:$USERNAME /opt/dynamo/venv
COPY --from=base --chown=$USERNAME:$USERNAME /usr/local/bin /usr/local/bin

USER $USERNAME
ENV HOME=/home/$USERNAME
ENV PYTHONPATH=/workspace/dynamo/deploy/sdk/src:/workspace/dynamo/components/planner/src:/workspace/examples/sglang:$PYTHONPATH
WORKDIR $HOME

# https://code.visualstudio.com/remote/advancedcontainers/persist-bash-history
RUN SNIPPET="export PROMPT_COMMAND='history -a' && export HISTFILE=$HOME/.commandhistory/.bash_history" \
    && mkdir -p $HOME/.commandhistory \
    && touch $HOME/.commandhistory/.bash_history \
    && echo "$SNIPPET" >> "$HOME/.bashrc"

RUN mkdir -p /home/$USERNAME/.cache/

ENV VLLM_KV_CAPI_PATH=$HOME/dynamo/.build/target/debug/libdynamo_llm_capi.so

ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]

##################################
##### Wheel Build Image ##########
##################################

# Redeclare ARCH_ALT ARG so it's available for interpolation in the FROM instruction
ARG ARCH_ALT

FROM quay.io/pypa/manylinux_2_28_${ARCH_ALT} AS wheel_builder

ARG CARGO_BUILD_JOBS
# Set CARGO_BUILD_JOBS to 16 if not provided
# This is to prevent cargo from building $(nproc) jobs in parallel,
# which might exceed the number of opened files limit.
ENV CARGO_BUILD_JOBS=${CARGO_BUILD_JOBS:-16}
# Use build arg RELEASE_BUILD = true to generate wheels for Python 3.10, 3.11 and 3.12.
ARG RELEASE_BUILD

WORKDIR /workspace

RUN yum update -y \
    && yum install -y llvm-toolset \
    && yum install -y python3.12-devel \
    && yum install -y protobuf-compiler \
    && yum clean all \
    && rm -rf /var/cache/yum

ENV RUSTUP_HOME=/usr/local/rustup \
    CARGO_HOME=/usr/local/cargo \
    CARGO_TARGET_DIR=/workspace/target \
    VIRTUAL_ENV=/opt/dynamo/venv

COPY --from=base $RUSTUP_HOME $RUSTUP_HOME
COPY --from=base $CARGO_HOME $CARGO_HOME
COPY --from=base /usr/local/nixl /opt/nvidia/nvda_nixl
COPY --from=base /workspace /workspace
COPY --from=base $VIRTUAL_ENV $VIRTUAL_ENV
ENV PATH=$CARGO_HOME/bin:$VIRTUAL_ENV/bin:$PATH

# Copy configuration files
COPY pyproject.toml /workspace/
COPY README.md /workspace/
COPY LICENSE /workspace/
COPY Cargo.toml /workspace/
COPY Cargo.lock /workspace/
COPY rust-toolchain.toml /workspace/
COPY hatch_build.py /workspace/

# Copy source code
COPY lib/ /workspace/lib/
COPY components /workspace/components
COPY launch /workspace/launch
COPY deploy/sdk /workspace/deploy/sdk

RUN cargo build \
	--release \
	--locked \
	--features dynamo-llm/block-manager \
	--workspace

# Build dynamo wheel
RUN uv build --wheel --out-dir /workspace/dist && \
    cd /workspace/lib/bindings/python && \
    uv pip install maturin[patchelf] && \
    maturin build --release --features block-manager --out /workspace/dist && \
    if [ "$RELEASE_BUILD" = "true" ]; then \
        uv run --python 3.11 maturin build --release --features block-manager --out /workspace/dist && \
        uv run --python 3.10 maturin build --release --features block-manager --out /workspace/dist; \
    fi

#######################################
########## CI Minimum Image ###########
#######################################
FROM base AS ci_minimum

ENV DYNAMO_HOME=/workspace
ENV CARGO_TARGET_DIR=/workspace/target

WORKDIR /workspace

COPY --from=wheel_builder /workspace /workspace
COPY --from=wheel_builder /opt/nvidia/nvda_nixl /opt/nvidia/nvda_nixl
# Copy Cargo cache to avoid re-downloading dependencies
COPY --from=wheel_builder $CARGO_HOME $CARGO_HOME

# Copy rest of the code
COPY . /workspace

# Build C bindings, creates lib/bindings/c/include
RUN cd /workspace/lib/bindings/c && cargo build --release --locked

# Package the bindings
RUN mkdir -p /opt/dynamo/bindings/wheels && \
    mkdir /opt/dynamo/bindings/lib && \
    cp dist/ai_dynamo*cp312*.whl /opt/dynamo/bindings/wheels/. && \
    cp target/release/libdynamo_llm_capi.so /opt/dynamo/bindings/lib/. && \
    cp -r lib/bindings/c/include /opt/dynamo/bindings/.  && \
    cp target/release/dynamo-run /usr/local/bin && \
    cp target/release/metrics /usr/local/bin && \
    cp target/release/mock_worker /usr/local/bin

RUN uv pip install /workspace/dist/ai_dynamo_runtime*cp312*.whl && \
    uv pip install /workspace/dist/ai_dynamo*any.whl

# Copy launch banner
RUN --mount=type=bind,source=./container/launch_message.txt,target=/workspace/launch_message.txt \
    sed '/^#\s/d' /workspace/launch_message.txt > ~/.launch_screen && \
    echo "cat ~/.launch_screen" >> ~/.bashrc

# Tell vllm to use the Dynamo LLM C API for KV Cache Routing
ENV VLLM_KV_CAPI_PATH=/opt/dynamo/bindings/lib/libdynamo_llm_capi.so
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/nvidia/nvda_nixl/lib/x86_64-linux-gnu/

ENV PYTHONPATH=/workspace/dynamo/deploy/sdk/src:/workspace/dynamo/components/planner/src:/workspace/examples/sglang/utils:$PYTHONPATH

########################################
########## Development Image ###########
########################################
FROM ci_minimum AS dev

ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]

CMD []

####################################
########## Runtime Image ###########
####################################

FROM ${RUNTIME_IMAGE}:${RUNTIME_IMAGE_TAG} AS runtime

WORKDIR /workspace
ENV DYNAMO_HOME=/workspace
ENV VIRTUAL_ENV=/opt/dynamo/venv
ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"

### COPY NATS & ETCD ###
# Copy nats and etcd from base image
COPY --from=base /usr/bin/nats-server /usr/bin/nats-server
COPY --from=base /usr/local/bin/etcd/ /usr/local/bin/etcd/
ENV PATH=/usr/local/bin/etcd/:$PATH

# Copy UCX from base image as plugin for NIXL
# Copy NIXL source from base image (required for NIXL plugins)
COPY --from=base /usr/local/ucx /usr/local/ucx
COPY --from=base /usr/local/nixl /usr/local/nixl
ARG ARCH_ALT
ENV NIXL_PLUGIN_DIR=/usr/local/nixl/lib/${ARCH_ALT}-linux-gnu/plugins
ENV LD_LIBRARY_PATH=/usr/local/nixl/lib/${ARCH_ALT}-linux-gnu:/usr/local/nixl/lib/${ARCH_ALT}-linux-gnu/plugins:/usr/local/ucx/lib:$LD_LIBRARY_PATH

# Setup the python environment
# libnuma-dev is a required dependency for sglang integration with NIXL
COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
RUN apt-get update && \
    DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends build-essential python3-dev libnuma-dev && \
    rm -rf /var/lib/apt/lists/* && \
    uv venv $VIRTUAL_ENV --python 3.12 && \
    echo "source $VIRTUAL_ENV/bin/activate" >> ~/.bashrc

# Install SGLang and related packages (sgl-kernel, einops, sentencepiece) since they are not included in the runtime wheel
# https://github.com/sgl-project/sglang/blob/v0.4.9.post1/python/pyproject.toml#L18-51
ARG SGLANG_VERSION
ARG SGL_KERNEL_VERSION
RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install sglang[runtime_common]==${SGLANG_VERSION} einops sgl-kernel==${SGL_KERNEL_VERSION} sentencepiece

# Install the wheels and symlink executables to /usr/local/bin so dynamo components can use them
# Dynamo components currently do not have the VIRTUAL_ENV in their PATH, so we need to symlink the executables
COPY --from=wheel_builder /workspace/dist/*.whl wheelhouse/
COPY --from=base /workspace/wheels/nixl/*.whl wheelhouse/
RUN uv pip install ai-dynamo nixl --find-links wheelhouse

# Tell vllm to use the Dynamo LLM C API for KV Cache Routing
ENV VLLM_KV_CAPI_PATH="/opt/dynamo/bindings/lib/libdynamo_llm_capi.so"

# Copy launch banner
RUN --mount=type=bind,source=./container/launch_message.txt,target=/workspace/launch_message.txt \
    sed '/^#\s/d' /workspace/launch_message.txt > ~/.launch_screen && \
    echo "cat ~/.launch_screen" >> ~/.bashrc

# Copy benchmarks, examples, and tests for CI
# TODO: Remove this once we have a functional CI image built on top of the runtime image
COPY tests /workspace/tests
COPY benchmarks /workspace/benchmarks
COPY examples /workspace/examples
RUN uv pip install /workspace/benchmarks

# Copy attribution files
COPY ATTRIBUTION* LICENSE /workspace/

ENV PYTHONPATH=/workspace/examples/sglang/utils:$PYTHONPATH

ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
CMD []