Dockerfile.sglang

# syntax=docker/dockerfile:1.10.0
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# NOTE FOR dynamo_base AND wheel_builder STAGES:
#
# All changes to dynamo_base and wheel_builder stages should be replicated across
# Dockerfile and Dockerfile.<framework> images.:
#   - Dockerfile
#   - Dockerfile.vllm
#   - Dockerfile.sglang
#   - Dockerfile.trtllm
# This duplication was introduced purposely to quickly enable Docker layer caching and
# deduplication. Please ensure these stages stay in sync until the duplication can be
# addressed.
#
# Throughout this file, we make certain paths group-writable because this allows
# both the dynamo user (UID 1000) and Dev Container users (UID != 1000) to work
# properly without needing slow chown -R operations (which can add 2-10 extra
# minutes).
#
# DEVELOPMENT PATHS THAT MUST BE GROUP-WRITABLE (for virtualenv containers):
#   /workspace            - Users create/modify project files
#   /home/dynamo          - Users create config/cache files
#   /home/dynamo/.local   - SGLang uses $HOME/.local/lib/python3.12/site-packages for pip install
#
# HOW TO ACHIEVE GROUP-WRITABLE PERMISSIONS:
# 1. SHELL + /etc/profile.d - Login shell sources umask 002 globally for all RUN commands (775/664)
# 2. COPY --chmod=775       - Sets permissions on copied children (not destination)
# 3. chmod g+w (no -R)      - Fixes destination dirs only (milliseconds vs minutes)

# This section contains build arguments that are common and shared with
# the plain Dockerfile, so they should NOT have a default. The source of truth is from build.sh.
ARG BASE_IMAGE
ARG BASE_IMAGE_TAG

ARG PYTHON_VERSION
ARG ENABLE_KVBM
ARG ENABLE_MEDIA_NIXL
ARG ENABLE_MEDIA_FFMPEG
ARG CARGO_BUILD_JOBS

ARG RUNTIME_IMAGE="lmsysorg/sglang"
ARG RUNTIME_IMAGE_TAG="v0.5.7-runtime"

# SCCACHE configuration
ARG USE_SCCACHE
ARG SCCACHE_BUCKET=""
ARG SCCACHE_REGION=""

# NIXL configuration
ARG NIXL_UCX_REF
ARG NIXL_REF
ARG NIXL_GDRCOPY_REF
ARG NIXL_LIBFABRIC_REF

# 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

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

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

ARG ARCH
ARG ARCH_ALT

USER root
WORKDIR /opt/dynamo

# Install uv package manager
COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/

# Install NATS server
ENV NATS_VERSION="v2.10.28"
RUN --mount=type=cache,target=/var/cache/apt \
    wget --tries=3 --waitretry=5 https://github.com/nats-io/nats-server/releases/download/${NATS_VERSION}/nats-server-${NATS_VERSION}-${ARCH}.deb && \
    dpkg -i nats-server-${NATS_VERSION}-${ARCH}.deb && rm nats-server-${NATS_VERSION}-${ARCH}.deb

# Install 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

# Rust Setup
# Rust environment setup
ENV RUSTUP_HOME=/usr/local/rustup \
    CARGO_HOME=/usr/local/cargo \
    PATH=/usr/local/cargo/bin:$PATH \
    RUST_VERSION=1.90.0

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

# Install Rust
RUN wget --tries=3 --waitretry=5 "https://static.rust-lang.org/rustup/archive/1.28.1/${RUSTARCH}/rustup-init" && \
    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


##################################
##### 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

# Redeclare ARGs for this stage
ARG ARCH
ARG ARCH_ALT
ARG CARGO_BUILD_JOBS

WORKDIR /workspace

# Copy CUDA from base stage
COPY --from=dynamo_base /usr/local/cuda /usr/local/cuda
COPY --from=dynamo_base /etc/ld.so.conf.d/hpcx.conf /etc/ld.so.conf.d/hpcx.conf

# Set environment variables first so they can be used in COPY commands
ENV CARGO_BUILD_JOBS=${CARGO_BUILD_JOBS:-16} \
    RUSTUP_HOME=/usr/local/rustup \
    CARGO_HOME=/usr/local/cargo \
    CARGO_TARGET_DIR=/opt/dynamo/target \
    PATH=/usr/local/cargo/bin:$PATH

# Copy artifacts from base stage
COPY --from=dynamo_base $RUSTUP_HOME $RUSTUP_HOME
COPY --from=dynamo_base $CARGO_HOME $CARGO_HOME
# Install system dependencies
RUN yum groupinstall -y 'Development Tools' &&  \
    dnf install -y almalinux-release-synergy && \
    dnf config-manager --set-enabled powertools && \
    dnf install -y \
        # Build tools
        cmake \
        ninja-build \
        clang-devel \
        # Install GCC toolset 14 (CUDA compatible, max version 14)
        gcc-toolset-14-gcc \
        gcc-toolset-14-gcc-c++ \
        gcc-toolset-14-binutils \
        flex \
        wget \
        # Kernel module build dependencies
        dkms \
        # Protobuf support
        protobuf-compiler \
        # RDMA/InfiniBand support (required for UCX build with --with-verbs)
        libibverbs \
        libibverbs-devel \
        rdma-core \
        rdma-core-devel \
        libibumad \
        libibumad-devel \
        librdmacm-devel \
        numactl-devel \
        # Libfabric support
        hwloc \
        hwloc-devel

# Set GCC toolset 14 as the default compiler (CUDA requires GCC <= 14)
ENV PATH="/opt/rh/gcc-toolset-14/root/usr/bin:${PATH}" \
    LD_LIBRARY_PATH="/opt/rh/gcc-toolset-14/root/usr/lib64:${LD_LIBRARY_PATH}" \
    CC="/opt/rh/gcc-toolset-14/root/usr/bin/gcc" \
    CXX="/opt/rh/gcc-toolset-14/root/usr/bin/g++"


# Ensure a modern protoc is available (required for --experimental_allow_proto3_optional)
RUN set -eux; \
    PROTOC_VERSION=25.3; \
    case "${ARCH_ALT}" in \
      x86_64) PROTOC_ZIP="protoc-${PROTOC_VERSION}-linux-x86_64.zip" ;; \
      aarch64) PROTOC_ZIP="protoc-${PROTOC_VERSION}-linux-aarch_64.zip" ;; \
      *) echo "Unsupported architecture: ${ARCH_ALT}" >&2; exit 1 ;; \
    esac; \
    wget --tries=3 --waitretry=5 -O /tmp/protoc.zip "https://github.com/protocolbuffers/protobuf/releases/download/v${PROTOC_VERSION}/${PROTOC_ZIP}"; \
    rm -f /usr/local/bin/protoc /usr/bin/protoc; \
    unzip -o /tmp/protoc.zip -d /usr/local bin/protoc include/*; \
    chmod +x /usr/local/bin/protoc; \
    ln -s /usr/local/bin/protoc /usr/bin/protoc; \
    protoc --version

# Point build tools explicitly at the modern protoc
ENV PROTOC=/usr/local/bin/protoc

ENV CUDA_PATH=/usr/local/cuda \
    PATH=/usr/local/cuda/bin:$PATH \
    LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/lib:/usr/local/lib64:$LD_LIBRARY_PATH \
    NVIDIA_DRIVER_CAPABILITIES=video,compute,utility

# Create virtual environment for building wheels
ARG PYTHON_VERSION
ENV VIRTUAL_ENV=/workspace/.venv
RUN uv venv ${VIRTUAL_ENV} --python $PYTHON_VERSION && \
    uv pip install --upgrade meson pybind11 patchelf maturin[patchelf] tomlkit

ARG NIXL_UCX_REF
ARG NIXL_REF
ARG NIXL_GDRCOPY_REF

# Build and install gdrcopy
RUN git clone --depth 1 --branch ${NIXL_GDRCOPY_REF} https://github.com/NVIDIA/gdrcopy.git && \
    cd gdrcopy/packages && \
    CUDA=/usr/local/cuda ./build-rpm-packages.sh && \
    rpm -Uvh gdrcopy-kmod-*.el8.noarch.rpm && \
    rpm -Uvh gdrcopy-*.el8.${ARCH_ALT}.rpm && \
    rpm -Uvh gdrcopy-devel-*.el8.noarch.rpm

# Install SCCACHE if requested
ARG USE_SCCACHE
ARG SCCACHE_BUCKET
ARG SCCACHE_REGION
COPY container/use-sccache.sh /tmp/use-sccache.sh
RUN if [ "$USE_SCCACHE" = "true" ]; then \
        /tmp/use-sccache.sh install; \
    fi

# Set SCCACHE environment variables
ENV SCCACHE_BUCKET=${USE_SCCACHE:+${SCCACHE_BUCKET}} \
    SCCACHE_REGION=${USE_SCCACHE:+${SCCACHE_REGION}}

# Build FFmpeg from source
# Do not delete the source tarball for legal reasons
ARG FFMPEG_VERSION=7.1
RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
if [ "$ENABLE_MEDIA_FFMPEG" = "true" ]; then \
    export SCCACHE_S3_KEY_PREFIX=${SCCACHE_S3_KEY_PREFIX:-${ARCH}} && \
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export RUSTC_WRAPPER="sccache"; \
    fi && \
    dnf install -y pkg-config && \
    cd /tmp && \
    curl -LO https://ffmpeg.org/releases/ffmpeg-${FFMPEG_VERSION}.tar.xz && \
    tar xf ffmpeg-${FFMPEG_VERSION}.tar.xz && \
    cd ffmpeg-${FFMPEG_VERSION} && \
    ./configure \
        --prefix=/usr/local \
        --disable-gpl \
        --disable-nonfree \
        --disable-programs \
        --disable-doc \
        --disable-static \
        --disable-x86asm \
        --disable-postproc \
        --disable-network \
        --disable-encoders \
        --disable-muxers \
        --disable-bsfs \
        --disable-devices \
        --disable-libdrm \
        --enable-shared && \
    make -j$(nproc) && \
    make install && \
    /tmp/use-sccache.sh show-stats "FFMPEG" && \
    ldconfig && \
    mkdir -p /usr/local/src/ffmpeg && \
    mv /tmp/ffmpeg-${FFMPEG_VERSION}* /usr/local/src/ffmpeg/; \
fi

# Build and install UCX
RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
    export SCCACHE_S3_KEY_PREFIX="${SCCACHE_S3_KEY_PREFIX:-${ARCH}}" && \
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CUDA_COMPILER_LAUNCHER="sccache"; \
    fi && \
    cd /usr/local/src && \
     git clone https://github.com/openucx/ucx.git && \
     cd ucx && 			     \
     git checkout $NIXL_UCX_REF &&	 \
     ./autogen.sh &&      \
     ./contrib/configure-release    \
        --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-dm                   \
        --with-gdrcopy=/usr/local   \
        --with-efa                  \
        --enable-mt &&              \
     make -j &&                      \
     make -j install-strip &&        \
     /tmp/use-sccache.sh show-stats "UCX" && \
     echo "/usr/local/ucx/lib" > /etc/ld.so.conf.d/ucx.conf && \
     echo "/usr/local/ucx/lib/ucx" >> /etc/ld.so.conf.d/ucx.conf && \
     ldconfig

ARG NIXL_LIBFABRIC_REF
RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
    export SCCACHE_S3_KEY_PREFIX="${SCCACHE_S3_KEY_PREFIX:-${ARCH}}" && \
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CUDA_COMPILER_LAUNCHER="sccache"; \
    fi && \
    cd /usr/local/src && \
    git clone https://github.com/ofiwg/libfabric.git && \
    cd libfabric && \
    git checkout $NIXL_LIBFABRIC_REF && \
    ./autogen.sh && \
    ./configure --prefix="/usr/local/libfabric" \
                --disable-verbs \
                --disable-psm3 \
                --disable-opx \
                --disable-usnic \
                --disable-rstream \
                --enable-efa \
                --with-cuda=/usr/local/cuda \
                --enable-cuda-dlopen \
                --with-gdrcopy \
                --enable-gdrcopy-dlopen && \
    make -j$(nproc) && \
    make install && \
    /tmp/use-sccache.sh show-stats "LIBFABRIC" && \
    echo "/usr/local/libfabric/lib" > /etc/ld.so.conf.d/libfabric.conf && \
    ldconfig

# build and install nixl
RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
    export SCCACHE_S3_KEY_PREFIX="${SCCACHE_S3_KEY_PREFIX:-${ARCH}}" && \
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CUDA_COMPILER_LAUNCHER="sccache"; \
    fi && \
    source ${VIRTUAL_ENV}/bin/activate && \
    git clone "https://github.com/ai-dynamo/nixl.git" && \
    cd nixl && \
    git checkout ${NIXL_REF} && \
    CUDA_MAJOR=$(nvcc --version | grep -Eo 'release [0-9]+\.[0-9]+' | cut -d' ' -f2 | cut -d'.' -f1) && \
    if [ "$CUDA_MAJOR" -ne 12 ] && [ "$CUDA_MAJOR" -ne 13 ]; then \
        echo "Invalid CUDA_MAJOR: '$CUDA_MAJOR'" && \
        exit 1; \
    fi && \
    PKG_NAME="nixl-cu${CUDA_MAJOR}" && \
    ./contrib/tomlutil.py --wheel-name $PKG_NAME pyproject.toml && \
    mkdir build && \
    meson setup build/ --prefix=/opt/nvidia/nvda_nixl --buildtype=release \
    -Dcudapath_lib="/usr/local/cuda/lib64" \
    -Dcudapath_inc="/usr/local/cuda/include" \
    -Ducx_path="/usr/local/ucx" \
    -Dlibfabric_path="/usr/local/libfabric" && \
    cd build && \
    ninja && \
    ninja install && \
    /tmp/use-sccache.sh show-stats "NIXL"

ENV NIXL_LIB_DIR=/opt/nvidia/nvda_nixl/lib64  \
    NIXL_PLUGIN_DIR=/opt/nvidia/nvda_nixl/lib64/plugins \
    NIXL_PREFIX=/opt/nvidia/nvda_nixl
ENV LD_LIBRARY_PATH=${NIXL_LIB_DIR}:${NIXL_PLUGIN_DIR}:/usr/local/ucx/lib:/usr/local/ucx/lib/ucx:${LD_LIBRARY_PATH}

RUN echo "$NIXL_LIB_DIR" > /etc/ld.so.conf.d/nixl.conf && \
    echo "$NIXL_PLUGIN_DIR" >> /etc/ld.so.conf.d/nixl.conf && \
    ldconfig

RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
    export SCCACHE_S3_KEY_PREFIX="${SCCACHE_S3_KEY_PREFIX:-${ARCH}}" && \
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CUDA_COMPILER_LAUNCHER="sccache"; \
    fi && \
    cd /workspace/nixl && \
    uv build . --wheel --out-dir /opt/dynamo/dist/nixl --python $PYTHON_VERSION

# Copy source code (order matters for layer caching)
COPY pyproject.toml README.md LICENSE Cargo.toml Cargo.lock rust-toolchain.toml hatch_build.py /opt/dynamo/
COPY launch/ /opt/dynamo/launch/
COPY lib/ /opt/dynamo/lib/
COPY components/ /opt/dynamo/components/

# Build dynamo wheels
ARG ENABLE_KVBM
RUN --mount=type=secret,id=aws-key-id,env=AWS_ACCESS_KEY_ID \
    --mount=type=secret,id=aws-secret-id,env=AWS_SECRET_ACCESS_KEY \
    export SCCACHE_S3_KEY_PREFIX=${SCCACHE_S3_KEY_PREFIX:-${ARCH}} && \
    if [ "$USE_SCCACHE" = "true" ]; then \
        export CMAKE_C_COMPILER_LAUNCHER="sccache" && \
        export CMAKE_CXX_COMPILER_LAUNCHER="sccache" && \
        export RUSTC_WRAPPER="sccache"; \
    fi && \
    source ${VIRTUAL_ENV}/bin/activate && \
    cd /opt/dynamo && \
    uv build --wheel --out-dir /opt/dynamo/dist && \
    cd /opt/dynamo/lib/bindings/python && \
    FEATURES=""; \
    if [ "$ENABLE_MEDIA_NIXL" = "true" ]; then \
        FEATURES="$FEATURES dynamo-llm/media-nixl"; \
    fi; \
    if [ "$ENABLE_MEDIA_FFMPEG" = "true" ]; then \
        FEATURES="$FEATURES media-ffmpeg"; \
    fi; \
    if [ -n "$FEATURES" ]; then \
        maturin build --release --features "$FEATURES" --out /opt/dynamo/dist; \
    else \
        maturin build --release --out /opt/dynamo/dist; \
    fi && \
    if [ "$ENABLE_KVBM" = "true" ]; then \
        cd /opt/dynamo/lib/bindings/kvbm && \
        maturin build --release --out target/wheels && \
        auditwheel repair \
            --exclude libnixl.so \
            --exclude libnixl_build.so \
            --exclude libnixl_common.so \
            --plat manylinux_2_28_${ARCH_ALT} \
            --wheel-dir /opt/dynamo/dist \
            target/wheels/*.whl; \
    fi && \
    /tmp/use-sccache.sh show-stats "Dynamo"

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

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

# cleanup unnecessary libs
RUN apt remove -y python3-apt &&\
    pip uninstall -y termplotlib

# This ARG is still utilized for SGLANG Version extraction
ARG RUNTIME_IMAGE_TAG
WORKDIR /workspace

# Install NATS and ETCD
COPY --from=dynamo_base /usr/bin/nats-server /usr/bin/nats-server
COPY --from=dynamo_base /usr/local/bin/etcd/ /usr/local/bin/etcd/

ENV PATH=/usr/local/bin/etcd:$PATH

# Create dynamo user with group 0 for OpenShift compatibility
RUN userdel -r ubuntu > /dev/null 2>&1 || true \
    && useradd -m -s /bin/bash -g 0 dynamo \
    && [ `id -u dynamo` -eq 1000 ] \
    && mkdir -p /home/dynamo/.cache /opt/dynamo \
    # Non-recursive chown - only the directories themselves, not contents
    && chown dynamo:0 /home/dynamo /home/dynamo/.cache /opt/dynamo /workspace \
    # No chmod needed: umask 002 handles new files, COPY --chmod handles copied content
    # Set umask globally for all subsequent RUN commands (must be done as root before USER dynamo)
    # NOTE: Setting ENV UMASK=002 does NOT work - umask is a shell builtin, not an environment variable
    && mkdir -p /etc/profile.d && echo 'umask 002' > /etc/profile.d/00-umask.sh

# Copy attribution files
COPY --chmod=664 --chown=dynamo:0 ATTRIBUTION* LICENSE /workspace/

# Copy ffmpeg
RUN --mount=type=bind,from=wheel_builder,source=/usr/local/,target=/tmp/usr/local/ \
    cp -rnL /tmp/usr/local/include/libav* /tmp/usr/local/include/libsw* /usr/local/include/; \
    cp -nL /tmp/usr/local/lib/libav*.so /tmp/usr/local/lib/libsw*.so /usr/local/lib/; \
    cp -nL /tmp/usr/local/lib/pkgconfig/libav*.pc /tmp/usr/local/lib/pkgconfig/libsw*.pc /usr/lib/pkgconfig/; \
    cp -r /tmp/usr/local/src/ffmpeg /usr/local/src/; \
    true # in case ffmpeg not enabled

# Pattern: COPY --chmod=775 <path>; chmod g+w <path> done later as root because COPY --chmod only affects <path>/*, not <path>
COPY --chmod=775 --chown=dynamo:0 benchmarks/ /workspace/benchmarks/
COPY --chmod=775 --chown=dynamo:0 --from=wheel_builder /opt/dynamo/dist/*.whl /opt/dynamo/wheelhouse/
COPY --chmod=775 --chown=dynamo:0 --from=wheel_builder /opt/dynamo/dist/nixl/ /opt/dynamo/wheelhouse/nixl/
COPY --chmod=775 --chown=dynamo:0 --from=wheel_builder /workspace/nixl/build/src/bindings/python/nixl-meta/nixl-*.whl /opt/dynamo/wheelhouse/nixl/

ENV SGLANG_VERSION="${RUNTIME_IMAGE_TAG%%-*}"
# Install packages as root to ensure they go to system location (/usr/local/lib/python3.12/dist-packages)
RUN --mount=type=bind,source=.,target=/mnt/local_src \
    pip install --no-cache-dir --break-system-packages \
        /opt/dynamo/wheelhouse/ai_dynamo_runtime*.whl \
        /opt/dynamo/wheelhouse/ai_dynamo*any.whl \
        /opt/dynamo/wheelhouse/nixl/nixl*.whl \
        sglang==${SGLANG_VERSION}

# Install common and test dependencies as root
RUN --mount=type=bind,source=.,target=/mnt/local_src \
    pip install --no-cache-dir --break-system-packages \
        --requirement /mnt/local_src/container/deps/requirements.txt \
        --requirement /mnt/local_src/container/deps/requirements.test.txt \
        sglang==${SGLANG_VERSION} && \
    cd /workspace/benchmarks && \
    pip install --break-system-packages --no-cache . && \
    # pip/uv bypasses umask when creating .egg-info files, but chmod -R is fast here (small directory)
    chmod -R g+w /workspace/benchmarks && \
    CUDA_MAJOR=$(nvcc --version | egrep -o 'cuda_[0-9]+' | cut -d_ -f2) && \
    if [ "$CUDA_MAJOR" = "12" ]; then \
        # Install NVIDIA packages that are needed for DeepEP to work properly
        # This is done in the upstream runtime image too, but these packages are overridden in earlier commands
        pip install --no-cache-dir --break-system-packages --force-reinstall --no-deps \
            nvidia-nccl-cu12==2.28.3 \
            nvidia-cudnn-cu12==9.16.0.29 \
            nvidia-cutlass-dsl==4.3.0; \
    fi

# Switch back to dynamo user after package installations
USER dynamo

# Copy tests, deploy and components for CI with correct ownership
# Pattern: COPY --chmod=775 <path>; chmod g+w <path> done later as root because COPY --chmod only affects <path>/*, not <path>
COPY --chmod=775 --chown=dynamo:0 tests /workspace/tests
COPY --chmod=775 --chown=dynamo:0 examples /workspace/examples
COPY --chmod=775 --chown=dynamo:0 deploy /workspace/deploy
COPY --chmod=775 --chown=dynamo:0 components/ /workspace/components/
COPY --chmod=775 --chown=dynamo:0 recipes/ /workspace/recipes/

# Enable forceful shutdown of inflight requests
ENV SGLANG_FORCE_SHUTDOWN=1

# Setup launch banner in common directory accessible to all users
RUN --mount=type=bind,source=./container/launch_message/runtime.txt,target=/opt/dynamo/launch_message.txt \
    sed '/^#\s/d' /opt/dynamo/launch_message.txt > /opt/dynamo/.launch_screen

# Our scripting assumes /workspace is where dynamo is located
# In order to maintain the ability to have sglang and dynamo
# in the same workspace, symlink /workspace to /sgl-workspace/dynamo
USER root

# Fix directory permissions: COPY --chmod only affects contents, not the directory itself
RUN chmod 755 /opt/dynamo/.launch_screen && \
    echo 'cat /opt/dynamo/.launch_screen' >> /etc/bash.bashrc && \
    ln -s /workspace /sgl-workspace/dynamo

USER dynamo
ARG DYNAMO_COMMIT_SHA
ENV DYNAMO_COMMIT_SHA=${DYNAMO_COMMIT_SHA}


###########################################################
########## Development (run.sh, runs as root user) ########
###########################################################
#
# PURPOSE: Local development environment for use with run.sh (not Dev Container plug-in)
#
# This stage runs as root and provides:
# - Development tools and utilities for local debugging
# - Support for vscode/cursor development outside the Dev Container plug-in
#
# Use this stage if you need a full-featured development environment with extra tools,
# but do not use it with the Dev Container plug-in.

FROM runtime AS dev

# Don't want ubuntu to be editable, just change uid and gid.
ARG WORKSPACE_DIR=/workspace

USER root
# Install utilities as root
RUN apt-get update -y && \
    apt-get install -y --no-install-recommends  \
    # Install utilities
    nvtop \
    wget \
    tmux \
    vim \
    git \
    openssh-client \
    iproute2 \
    rsync \
    zip \
    unzip \
    htop \
    # Build Dependencies
    autoconf \
    automake \
    cmake \
    libtool \
    meson \
    net-tools \
    pybind11-dev \
    # Rust build dependencies
    clang \
    libclang-dev \
    protobuf-compiler \
    pkg-config && \
    rm -rf /var/lib/apt/lists/*

# Set umask for group-writable files in dev stage (runs as root)
RUN mkdir -p /etc/profile.d && echo 'umask 002' > /etc/profile.d/00-umask.sh
SHELL ["/bin/bash", "-l", "-o", "pipefail", "-c"]

# Set workspace directory variable
ENV WORKSPACE_DIR=${WORKSPACE_DIR} \
    DYNAMO_HOME=${WORKSPACE_DIR} \
    RUSTUP_HOME=/usr/local/rustup \
    CARGO_HOME=/usr/local/cargo \
    CARGO_TARGET_DIR=/workspace/target \
    PATH=/usr/local/cargo/bin:$PATH

# Copy rust installation from dynamo_base to avoid duplication efforts
# Pattern: COPY --chmod=775 <path>; chmod g+w <path> because COPY --chmod only affects <path>/*, not <path>
COPY --from=dynamo_base --chmod=775 /usr/local/rustup /usr/local/rustup
COPY --from=dynamo_base --chmod=775 /usr/local/cargo /usr/local/cargo
RUN chmod g+w /usr/local/rustup /usr/local/cargo

ARG ARCH
ARG ARCH_ALT

# Copy UCX and NIXL libraries for dev stage compilation
# The upstream SGLang runtime image doesn't include NIXL, but cargo build needs to link against
# -lnixl, -lnixl_build, and -lnixl_common. Runtime stage doesn't need this since it uses pre-built
# wheels, but dev stage needs it for maturin develop and cargo build from source.
COPY --from=wheel_builder /usr/local/ucx /usr/local/ucx
COPY --from=wheel_builder /opt/nvidia/nvda_nixl /opt/nvidia/nvda_nixl
COPY --from=wheel_builder /opt/nvidia/nvda_nixl/lib64/. /opt/nvidia/nvda_nixl/lib/${ARCH_ALT}-linux-gnu/

# Set NIXL environment variables for compilation
ENV NIXL_PREFIX=/opt/nvidia/nvda_nixl \
    NIXL_LIB_DIR=/opt/nvidia/nvda_nixl/lib/${ARCH_ALT}-linux-gnu \
    NIXL_PLUGIN_DIR=/opt/nvidia/nvda_nixl/lib/${ARCH_ALT}-linux-gnu/plugins

# Update LD_LIBRARY_PATH to include NIXL libraries for the linker
ENV LD_LIBRARY_PATH=\
${NIXL_LIB_DIR}:\
${NIXL_PLUGIN_DIR}:\
/usr/local/ucx/lib:\
/usr/local/ucx/lib/ucx:\
${LD_LIBRARY_PATH}

# Create virtual environment for maturin develop (required by maturin develop command)
# Use --system-site-packages to inherit sglang, torch, etc. from upstream
RUN mkdir -p /opt/dynamo/venv && \
    python3 -m venv --system-site-packages /opt/dynamo/venv

ENV VIRTUAL_ENV=/opt/dynamo/venv \
    PATH="/opt/dynamo/venv/bin:${PATH}"

# Copy all packages from runtime stage system site-packages into venv
# This includes ai-dynamo-runtime, kubernetes, and all other dependencies
# Use --no-preserve=mode so copied files inherit umask 002 (group-writable)
RUN cp -r --no-preserve=mode /usr/local/lib/python3.12/dist-packages/* \
          /opt/dynamo/venv/lib/python3.12/site-packages/

# Install maturin and uv into venv for development
# Uninstall broken maturin from upstream, then reinstall properly into venv
COPY --from=dynamo_base /bin/uv /opt/dynamo/venv/bin/uv
RUN pip install --ignore-installed maturin[patchelf]

# Editable install of dynamo components
COPY --chown=dynamo:0 --chmod=664 pyproject.toml README.md hatch_build.py /workspace/
RUN pip install --no-deps -e .

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