Dynamia ascend-device-plugin Chart 0.2.0
Release date: 2026-08-18
This page compares the release with the previous Chart package, GitHub Release Chart 0.1.1, published on 2026-08-17.
| Version | Previous | This release |
|---|---|---|
| Chart | 0.1.1 | 0.2.0 |
| appVersion | v1.4.0 | v1.4.0 |
HAMi Enterprise compatibility
| Feature or mode | Minimum usable HAMi Enterprise version | Compatibility requirements and upgrade conclusion |
|---|---|---|
| Template-based virtual NPU (vNPU) hard partitioning that directly reuses Enterprise shared-device configuration | v2.9.0-rc0 | With this version, the existing scheduler and shared-device configuration can be retained; this Chart update does not require an Enterprise upgrade. A separate plugin configuration in the new format with an older scheduler is another possible setup and is outside this version floor; verify it against the actual deployment. |
hami-core static soft partitioning | v2.9.0-rc0 | Enable the relevant device configuration and set huawei.com/vnpu-mode: hami-core on workloads. This compatible version injects a bash startup hook into containers without a custom PostStart, so the container must be able to run the hook. This Chart update does not change that requirement. |
Changes
This release only changes the Chart version from 0.1.1 to 0.2.0. The values, resource templates, appVersion, and default plugin image reference are identical between the two versions; both default to ghcr.io/dynamia-ai/ascend-device-plugin:v1.4.0. No application feature or configuration option was added.
Upgrade guidance
- Upgrade the Chart through the existing Helm process. This update does not require changes to values or HAMi Enterprise version. The Chart version change updates the resource
helm.sh/chartlabel and changes the DaemonSetchecksum/configannotation. As a result, device-plugin Pods roll even when configuration and the default image are unchanged. Confirm the DaemonSet rollout completes. - The application version does not change, so there is no need to recreate workload Pods to obtain new features. If
image.tagorimage.digestis pinned during installation, those overrides remain in effect; this release does not replace a custom image. - A historical GHCR OCI package also uses Chart version
0.1.1but defaults to plugin imagev1.3.0. If the existing installation came from that package, first verify the image actually in use, then assess the application changes from this release's defaultv1.4.0. Do not apply the “application version unchanged” conclusion on this page to that installation without checking.
See the Chart and appVersion mapping or the software center.
Values reference
The following parameter descriptions are taken from the README bundled with the Chart 0.2.0 release package and are preserved as published. Use this version's values.yaml as the source of default configuration.
Expand values table
| Key | Type | Default | Description |
|---|---|---|---|
| config.create | bool | false | Create the bundled device configuration ConfigMap for an installation without HAMi. Leave disabled when HAMi owns the device configuration. |
| config.deviceConfigMapName | string | "hami-scheduler-device" | Name of the device configuration ConfigMap created when config.create=true. |
| config.existingDeviceConfigMapName | string | "hami-scheduler-device" | HAMi-managed device configuration ConfigMap to reuse when config.create=false. The ConfigMap must be in the release namespace. |
| daemonSet.args[0] | string | "--config_file" | |
| daemonSet.args[1] | string | "/device-config.yaml" | |
| daemonSet.args[2] | string | "--v=4" | |
| daemonSet.args[3] | string | "--node_config_file" | |
| daemonSet.args[4] | string | "/node-config.yaml" | |
| daemonSet.name | string | "hami-ascend-device-plugin" | Device plugin DaemonSet name. |
| fullnameOverride | string | "" | Override the fully qualified resource name. |
| hamiVnpuCore.enabled | bool | false | Enable hami-vnpu-core in the bundled device configuration when config.create=true. This mode requires the HAMi scheduler. |
| image.digest | string | "" | Optional immutable OCI manifest digest. When set, it takes precedence over image.tag. |
| image.pullPolicy | string | "IfNotPresent" | Kubernetes image pull policy. |
| image.repository | string | "ghcr.io/dynamia-ai/ascend-device-plugin" | Container image repository. |
| image.tag | string | "v1.4.0" | Container image tag. |
| nameOverride | string | "" | Override the chart name used in resource names. |
| nodeConfig | string | "nodes: []" | Per-node hami-vnpu-core configuration written to the node ConfigMap. |
| nodeConfigMap.create | bool | true | Create the per-node configuration ConfigMap. |
| nodeConfigMap.name | string | "hami-device-node-config" | Per-node configuration ConfigMap name. |
| nodeSelector.ascend | string | "on" | Node label value used to schedule the device plugin. |
| rbac.name | string | "hami-ascend" | Name shared by the chart-managed RBAC resources. |
| resources.limits.cpu | string | "500m" | |
| resources.limits.memory | string | "500Mi" | |
| resources.requests.cpu | string | "500m" | |
| resources.requests.memory | string | "500Mi" | |
| runtimeClass.create | bool | true | Create the Ascend RuntimeClass. |
| runtimeClass.handler | string | "ascend" | Container runtime handler used by the RuntimeClass. |
| runtimeClass.name | string | "ascend" | RuntimeClass resource name. |
| serviceAccount.create | bool | true | Create a ServiceAccount for the device plugin. |
| serviceAccount.name | string | "hami-ascend" | ServiceAccount name. |
| vnpuMonitor.enabled | bool | false | Expose device plugin metrics and create optional Prometheus Operator resources. |
| vnpuMonitor.prometheusRule.create | bool | true | Create a PrometheusRule when vnpuMonitor.enabled=true. |
| vnpuMonitor.prometheusRule.groupLabels.vendor | string | "ascend" | |
| vnpuMonitor.prometheusRule.groupName | string | "ascend-vnpu" | Recording-rule group name. |
| vnpuMonitor.prometheusRule.interval | string | "15s" | Recording-rule evaluation interval. |
| vnpuMonitor.prometheusRule.labels.release | string | "prometheus" | |
| vnpuMonitor.prometheusRule.labels.role | string | "recording-rules" | |
| vnpuMonitor.prometheusRule.labels.vendor | string | "ascend" | |
| vnpuMonitor.prometheusRule.name | string | "hami-ascend-vnpu-monitor" | PrometheusRule resource name. |
| vnpuMonitor.prometheusRule.namespace | string | "monitoring" | Namespace for the PrometheusRule. |
| vnpuMonitor.service.name | string | "hami-ascend-device-plugin-metrics" | Headless Service that exposes the device plugin metrics port. |
| vnpuMonitor.serviceMonitor.create | bool | true | Create a ServiceMonitor when vnpuMonitor.enabled=true. |
| vnpuMonitor.serviceMonitor.interval | string | "15s" | Prometheus scrape interval. |
| vnpuMonitor.serviceMonitor.labels.release | string | "prometheus" | |
| vnpuMonitor.serviceMonitor.name | string | "hami-ascend-vnpu-monitor" | ServiceMonitor resource name. |
| vnpuMonitor.serviceMonitor.namespace | string | "monitoring" | Namespace for the ServiceMonitor. |
| vnpuMonitor.serviceMonitor.path | string | "/metrics" | Metrics HTTP path. |