Dockerfile.extention.awsefa

# Base Image support aws EFA
# Build Image with frameworks based on this
FROM verlai/verl:app-verl0.5-sglang0.4.6.post5-mcore0.12.2

# For aws instances with EFA net interface (Sagemaker AI Pod)
#     install EFA driver:
######## AWS EFA ############
ENV NCCL_VERSION=2.25.1-1
ENV DEBIAN_FRONTEND=noninteractive
ENV EFA_INSTALLER_VERSION=1.40.0
ENV AWS_OFI_NCCL_VERSION=1.14.2
ENV FI_EFA_SET_CUDA_SYNC_MEMOPS=0
ENV FI_PROVIDER=efa

RUN apt update && apt install -y linux-image-generic libhwloc-dev

RUN cd /tmp && \
    curl -O https://efa-installer.amazonaws.com/aws-efa-installer-${EFA_INSTALLER_VERSION}.tar.gz  && \
    tar -xf aws-efa-installer-${EFA_INSTALLER_VERSION}.tar.gz && \
    cd aws-efa-installer && \
    ./efa_installer.sh -y -g --skip-kmod --skip-limit-conf --no-verify && \
    ldconfig && \
    rm -rf /tmp/aws-efa-installer /var/lib/apt/lists/*

# NCCL EFA Plugin
RUN cd /tmp && \
    curl -LO https://github.com/aws/aws-ofi-nccl/archive/refs/tags/v${AWS_OFI_NCCL_VERSION}.tar.gz && \
    tar -xzf /tmp/v${AWS_OFI_NCCL_VERSION}.tar.gz && \
    rm /tmp/v${AWS_OFI_NCCL_VERSION}.tar.gz && \
    mv aws-ofi-nccl-${AWS_OFI_NCCL_VERSION} aws-ofi-nccl && \
    cd /tmp/aws-ofi-nccl && \
    ./autogen.sh && \
    ./configure --prefix=/opt/amazon/efa \
    --with-libfabric=/opt/amazon/efa \
    --with-cuda=/usr/local/cuda \
    --enable-platform-aws \
    --with-mpi=/opt/amazon/openmpi && \
    make -j$(nproc) install && \
    rm -rf /tmp/aws-ofi/nccl

# NCCL
RUN echo "/usr/local/lib"      >> /etc/ld.so.conf.d/local.conf && \
    echo "/opt/amazon/openmpi/lib" >> /etc/ld.so.conf.d/efa.conf && \
    ldconfig

ENV OMPI_MCA_pml=^cm,ucx            \
    OMPI_MCA_btl=tcp,self           \
    OMPI_MCA_btl_tcp_if_exclude=lo,docker0,veth_def_agent \
    OPAL_PREFIX=/opt/amazon/openmpi \
    NCCL_SOCKET_IFNAME=^docker,lo,veth_def_agent  \
    FI_EFA_USE_HUGE_PAGE=0

# docker build -t verl:awsefa --label "commit=$(git rev-parse --short HEAD)" .
# on aws:
# docker run --ipc=host --privileged --name verldev --gpus all --network=host --shm-size=1800gb -itd verl:awsefa