dynamo

MODELEXPRESS_VERSION=0.4.0 ENABLE_GPU_MEMORY_SERVICE=true DYNAMO_COMMIT_SHA=919682da679aa699d5bca9c872f4c1d9a530bbc0 EFA_VERSION=1.47.0 NIXL_LIBFABRIC_REF=v2.5.1 EFA_PC=$(find /opt/amazon/efa -path '*/pkgconfig/libfabric.pc' 2>/dev/null | head -n1) &&
  EFA_LIBFABRIC_RAW=$(cat "$EFA_PC" 2>/dev/null | grep '^Version:' | awk '{print $2}') &&
  EFA_LIBFABRIC_VER=$(echo "$EFA_LIBFABRIC_RAW" | grep -oE '^[0-9]+\.[0-9]+(\.[0-9]+)?') &&
  REF_VER=$(echo "${NIXL_LIBFABRIC_REF}" | sed 's/^v//') &&
  if [ -n "$EFA_LIBFABRIC_VER" ] &&
  [ -n "$REF_VER" ] &&
  [ "$(printf '%s\n' "$EFA_LIBFABRIC_VER" "$REF_VER" | sort -V | head -n1)" = "$EFA_LIBFABRIC_VER" ] &&
  [ "$EFA_LIBFABRIC_VER" != "$REF_VER" ]; then rm -rf /opt/amazon/efa &&
  cp -Pfr /tmp/libfabric_build /opt/amazon/efa &&
  sed -i 's|^prefix=.*|prefix=/opt/amazon/efa|' /opt/amazon/efa/lib/pkgconfig/libfabric.pc &&
  echo "/opt/amazon/efa/lib" > /etc/ld.so.conf.d/000_efa.conf &&
  rm -f /etc/ld.so.conf.d/efa.conf &&
  ldconfig &&
  echo "[aws] libfabric overlay: ${REF_VER} (overwrites EFA stock ${EFA_LIBFABRIC_RAW})"; else echo "[aws] libfabric overlay: skipped (EFA stock ${EFA_LIBFABRIC_RAW:-unknown} >= ${REF_VER})"; fi

NIXL_LIBFABRIC_REF=v2.5.1

EFA_VERSION=1.47.0

MODELEXPRESS_VERSION=0.4.0 ENABLE_GPU_MEMORY_SERVICE=true DYNAMO_COMMIT_SHA=919682da679aa699d5bca9c872f4c1d9a530bbc0 EFA_VERSION=1.47.0 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 /etc/ld.so.conf.d/aws-ofi-nccl.conf &&
  ldconfig

root

EFA_VERSION=1.47.0

—

/opt/nvidia/nvidia_entrypoint.sh

DYNAMO_COMMIT_SHA=919682da679aa699d5bca9c872f4c1d9a530bbc0