Install HAMi Ascend Device Plugin
Install Alauda Build of HAMi Ascend Device Plugin when Ascend devices must be exposed through HAMi-managed whole-card allocation, hard slicing, or soft slicing. It is delivered as an Operator Bundle and managed through a HAMiAscendDevicePlugin custom resource. Do not substitute a standalone DaemonSet installation for this ACP-managed component.
Review the v1.4.1 release notes, including the Ascend 310P-only validation scope and known hardware limitations, before use.
TOC
Before you beginInstall the Operator BundleConfigure the instanceVerify the installationNext stepsBefore you begin
- Install Alauda Build of HAMi and enable
Enable Ascendin its cluster plugin form. - Install the supported
Alauda Build of NPU Operatorpackage and prepare the Ascend Driver, OCI Runtime,ascendRuntimeClass, and node health through the Ascend NPU vendor base documentation. Confirm the NPU Operator and Driver combination for the target ACP release before installation. - Confirm the supported HAMi and HAMi Ascend Device Plugin combination in Versions and Components.
- Label each target node with
ascend=onunless the installed product configuration uses a different value. - Complete Switch the Ascend Device Plugin Owner and confirm that the native Ascend Device Plugin has stopped before creating the
HAMiAscendDevicePlugininstance. Do not edit the generatedNPUClusterPolicyor DaemonSet. - Confirm that the
ascendRuntimeClass exists. An admitted HAMi workload must haveruntimeClassName: ascend; set it in the manifest unless the NPU Operator webhook or HAMi scheduler is configured to inject it. Use only one RuntimeClass injector.
Apply the default node label when it matches the installed product configuration:
NPU Operator remains installed for HAMi-managed Ascend allocation. Keep its Driver, OCI Runtime, ascend RuntimeClass, and any required Exporter components running; disable only its native Device Plugin through the owner-switch procedure.
Install the Operator Bundle
-
Retrieve
Alauda Build of HAMi Ascend Device Pluginfrom Customer Portal and upload the Operator Bundle to ACP. -
In ACP, open
Administrator->Marketplace->OperatorHub, switch to the target cluster, and installAlauda Build of HAMi Ascend Device Plugin. -
Check the OLM resources. If the Subscription uses manual approval, review and approve the generated InstallPlan.
The ClusterServiceVersion must reach
Succeededbefore you continue. -
Create the
HAMiAscendDevicePlugininstance from the product form. Complete Namespace and the other required settings described in Configure the instance before creating it. Then verify the instance in the selected namespace:
Configure the instance
Review the following settings before creating the instance. Keep the defaults only when they match the target nodes and existing platform-owned resources.
Create the HAMiAscendDevicePlugin instance in kube-system, where the default HAMi installation creates hami-scheduler-device. The HAMi Operator and Hami custom resource normally use hami-system; do not use that namespace for the ADP instance or shared device ConfigMap.
Set Ascend Driver Host Path according to the driver deployment:
- Host Driver:
/usr/local/Ascend/driver - Alauda OS Runtime Driver:
/run/ascend/driver
Before creating the instance, decide whether each target node will serve whole-card workloads, hard slicing, or soft slicing. Whole-card requests do not depend on the partial-memory node mode. For hard or soft slicing in the v1.4.1 Alauda delivery, set the intended per-node value through the structured spec.nodeConfig object; do not rely on spec.hamiVnpuCore.enabled alone while the instance reuses the HAMi-owned ConfigMap.
Use Configure Ascend Slicing Mode for the complete mode mapping, YAML update, vDeviceCount guidance, rollout command, and result interpretation. Use the whole-card or hard- and soft-slice pages for workload requests.
Verify the installation
-
Check the two namespaces separately. The default HAMi Operator and
Hamiresource are inhami-system; the scheduler,hami-scheduler-device, andHAMiAscendDevicePluginoperand are inkube-system. Replace<hami-namespace>withkube-systemfor the following checks: -
Check the operator and DaemonSet:
-
Confirm that only the selected device-plugin owner is Ready on the target nodes:
-
Confirm the actual resource names exposed by the installed package:
Continue only when the node reports the expected HAMi-managed Ascend resources.
For an installation intended for soft slicing, run the effective-mode and scheduler-configuration checks in Configure Ascend Slicing Mode. Continue only when the target node reports hami-vnpu-core=true and the installed configuration contains the model-specific count and memory mappings. Use an optional core key only when that model declares resourceCoreName.
-
For each representative workload, verify the runtime and device access:
The RuntimeClass must be
ascend. Runnpu-smi infoand a device-memory or inference workload to confirm that the Pod can use the assigned device. Use the whole-card manifest or hard- and soft-slice manifests for this check.