Dockerfile.aws

# syntax=docker/dockerfile:1.10.0
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# PURPOSE: AWS EFA support layer
#
# This Dockerfile adds AWS EFA (Elastic Fabric Adapter) support on top of
# the runtime or dev stages from framework Dockerfiles (vllm, sglang, trtllm).
#
# Usage (via build.sh with --make-efa flag):
#   ./build.sh --framework vllm --target runtime --make-efa
#   ./build.sh --framework vllm --target local-dev --make-efa

ARG BASE_IMAGE
ARG EFA_VERSION

###########################################################
########## Runtime with AWS EFA ##########################
###########################################################
#
# This stage extends the runtime stage with AWS EFA installer
# which includes: libfabric and aws-ofi-nccl plugin
#
# Use this stage when deploying on AWS infrastructure with EFA support

FROM ${BASE_IMAGE} AS runtime-aws

ARG EFA_VERSION

USER root

# Install AWS EFA installer with bundled libfabric and aws-ofi-nccl
# Flags explanation:
#   --skip-kmod: Skip kernel module installation (handled by host)
#   --skip-limit-conf: Skip ulimit configuration (handled by container runtime)
#   --no-verify: Skip GPG verification (optional, can be removed if verification is needed)
RUN mkdir -p /tmp/efa && \
    cd /tmp/efa && \
    curl --retry 3 --retry-delay 2 -fsSL -o aws-efa-installer-${EFA_VERSION}.tar.gz \
        https://efa-installer.amazonaws.com/aws-efa-installer-${EFA_VERSION}.tar.gz && \
    tar -xf aws-efa-installer-${EFA_VERSION}.tar.gz && \
    cd aws-efa-installer && \
    apt-get update && \
    ./efa_installer.sh -y --skip-kmod --skip-limit-conf --no-verify && \
    rm -rf /tmp/efa && \
    rm -rf /opt/amazon/aws-ofi-nccl && \
    ldconfig

ENV EFA_VERSION="${EFA_VERSION}"

USER dynamo

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

########################################################################
########## Development with AWS EFA (run.sh, runs as root user) ########
########################################################################
#
# PURPOSE: Development environment with AWS EFA support
#
# This stage extends dev stages with development tools for building and
# debugging on EFA-enabled AWS instances.

FROM ${BASE_IMAGE} AS dev-aws

ARG EFA_VERSION

# Dev stage runs as root, no USER switch needed
# Install AWS EFA installer with bundled libfabric and aws-ofi-nccl
# Flags explanation:
#   --skip-kmod: Skip kernel module installation (handled by host)
#   --skip-limit-conf: Skip ulimit configuration (handled by container runtime)
#   --no-verify: Skip GPG verification (optional, can be removed if verification is needed)
RUN mkdir -p /tmp/efa && \
    cd /tmp/efa && \
    curl --retry 3 --retry-delay 2 -fsSL -o aws-efa-installer-${EFA_VERSION}.tar.gz \
        https://efa-installer.amazonaws.com/aws-efa-installer-${EFA_VERSION}.tar.gz && \
    tar -xf aws-efa-installer-${EFA_VERSION}.tar.gz && \
    cd aws-efa-installer && \
    apt-get update && \
    ./efa_installer.sh -y --skip-kmod --skip-limit-conf --no-verify && \
    rm -rf /tmp/efa && \
    rm -rf /opt/amazon/aws-ofi-nccl && \
    ldconfig

ENV EFA_VERSION="${EFA_VERSION}"

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