feat: on arm64 (Grace-Blackwell GB200/GB300) skip fabric manager and install nvidia-imex

download.sh

@@ -48,11 +48,40 @@ install_fabric_manager () {
     mv /opt/gpu/fm_run_package_installer.sh /opt/gpu/fabricmanager-linux-${NVIDIA_FM_ARCH}-${DRIVER_VERSION}/sbin/fm_run_package_installer.sh
 }
 
-if [[ "${DRIVER_KIND}" == "cuda" ]]; then
-    # download fabricmanager for nvlink based systems, e.g. multi instance gpu vms.
+install_imex () {
+    # nvidia-imex is the cross-node NVLink (MNNVL / ComputeDomains) coordinator for
+    # Grace-Blackwell. It is NOT in the driver .run or the fabric-manager redist -- it
+    # ships only as a separate deb in the CUDA repo. Bundle the version-matched deb into
+    # the image; it is installed at node boot (see install.sh device_init). The exact deb
+    # revision suffix (e.g. -1ubuntu1) varies by version, so resolve the filename from the
+    # repo Packages index rather than hard-coding it.
+    local repo="https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${VERSION_ID//./}/sbsa"
+    local deb
+    # NB: awk must read to EOF (no early `exit`) -- exiting mid-stream closes the pipe and
+    # SIGPIPEs curl, which `set -o pipefail` would turn into a build failure. Gate on a flag
+    # to keep only the first match instead.
+    deb="$(curl -fsSL "${repo}/Packages" \
+        | awk -v p="nvidia-imex_${DRIVER_VERSION}-" '$1=="Filename:" && index($2,p) && !f{print $2; f=1}')"
+    if [[ -z "${deb}" ]]; then
+        echo "nvidia-imex ${DRIVER_VERSION} not found in ${repo}"
+        exit 1
+    fi
+    curl -fsSLO "${repo}/${deb#./}"
+    mv "$(basename "${deb}")" /opt/gpu/
+}
+
+# download fabricmanager for nvlink based systems, but skip it on arm64:
+# arm64 = Grace-Blackwell (GB200/GB300), which uses IMEX, not a node-local FM.
+if [[ "${DRIVER_KIND}" == "cuda" && "${TARGETARCH}" != "arm64" ]]; then
    install_fabric_manager
 fi
 
+# download nvidia-imex for nvlink based arm64 systems (Grace-Blackwell GB200/GB300):
+# GB uses IMEX (not a node-local fabric manager) to coordinate cross-node NVLink.
+if [[ "${DRIVER_KIND}" == "cuda" && "${TARGETARCH}" == "arm64" ]]; then
+   install_imex
+fi
+
 
 # configure nvidia apt repo to cache packages
 curl -fsSLO https://nvidia.github.io/libnvidia-container/gpgkey

install.sh

@@ -159,14 +159,23 @@ device_init() {
     cp -r /usr/bin/lib64/lib64/* "/usr/lib/${ARCH}-linux-gnu/"
     nvidia-smi
 
-    # install fabricmanager for nvlink based systems
-    if [[ "${DRIVER_KIND}" == "cuda" ]]; then
-        NVIDIA_FM_ARCH=$ARCH
-        if [ "$NVIDIA_FM_ARCH" = "arm64" ]; then
-            # NVIDIA uses the name "SBSA" for ARM64 platforms for the fabric manager. See https://en.wikipedia.org/wiki/Server_Base_System_Architecture
-            NVIDIA_FM_ARCH="sbsa"
-        fi
-        bash /opt/gpu/fabricmanager-linux-${NVIDIA_FM_ARCH}-${DRIVER_VERSION}/sbin/fm_run_package_installer.sh
+    # install fabricmanager for nvlink based systems, but skip it on arm64:
+    # arm64 = Grace-Blackwell (GB200/GB300), which uses IMEX, not a node-local FM.
+    # (uname -m reports "aarch64" for arm64.)
+    if [[ "${DRIVER_KIND}" == "cuda" && "${ARCH}" != "aarch64" ]]; then
+        bash /opt/gpu/fabricmanager-linux-${ARCH}-${DRIVER_VERSION}/sbin/fm_run_package_installer.sh
+    fi
+
+    # install nvidia-imex on arm64 (Grace-Blackwell): the cross-node NVLink (MNNVL)
+    # coordinator that GB uses in place of a node-local fabric manager. The binary must be
+    # present on the host so the NVIDIA DRA driver (ComputeDomains) can inject it into its
+    # per-workload IMEX daemon pods. --force-depends: the deb declares nvidia-modprobe,
+    # which is provided by the runfile driver (present on disk) rather than as a deb.
+    # The node-wide nvidia-imex.service stays OFF -- IMEX is orchestrated per ComputeDomain
+    # by DRA, not run cluster-wide from the host.
+    if [[ "${DRIVER_KIND}" == "cuda" && "${ARCH}" == "aarch64" ]]; then
+        dpkg -i --force-depends /opt/gpu/nvidia-imex_*_arm64.deb
+        systemctl disable --now nvidia-imex.service 2>/dev/null || true
     fi
 
     mkdir -p /etc/containerd/config.d