aiDAPTIVCache Operator

This guide demonstrates how to install the aiDAPTIVCache Operator, which is required for Kubernetes to recognize and utilize Phison aiDAPTIVCache devices (phison.com/ai100).

Prerequisites

Before installing the operator, ensure you have:

• Access to OtterScale platform with Application management permissions
• A Kubernetes cluster with Phison aiDAPTIVCache hardware installed
• Sufficient cluster resources for the operator deployment

Note

The aiDAPTIVCache Operator must be installed before deploying any workloads that require Phison aiDAPTIVCache devices. Without this operator, Kubernetes will not be able to recognize or allocate aiDAPTIVCache resources.

Installation Steps

1. Navigate to Application Store

   In the OtterScale web interface:

   • Go to Application → Store
   • This opens the Helm chart repository

2. Add the aiDAPTIVCache Operator Chart

   Click Import button and provide the following information:

   • Chart URL:

     https://github.com/otterscale/charts/releases/download/aidaptivcache-operator-0.4.3/aidaptivcache-operator-0.4.3.tgz

   Click Confirm to import the chart into your store.

3. Install the Operator

   • Find aidaptivcache-inference in the Store list
   • Click the Install button
   • In the Install Release dialog:
     • Enter a Name for your deployment (e.g., aidaptivcache-operator)
     • Enter a Namespace (e.g., aidaptivcache-operator)
     • Click View/Edit button to open the configuration editor

   Tip

   The operator uses default values that work for most deployments. You can view the configuration by clicking View/Edit if you need to customize settings such as resource limits or node selectors.

What the Operator Does

The aiDAPTIVCache Operator performs the following functions:

• Resource Manager: Manage aiDAPTIVCache devices
• Device Discovery: Automatically detects Phison aiDAPTIVCache devices on cluster nodes
• Device Plugin: Registers aiDAPTIVCache devices as Kubernetes resources, enabling targeted workload scheduling
• Exporter: Exposes metrics and cache information via an NVMe exporter

Caution

Important: Do not uninstall the operator while workloads are using aiDAPTIVCache devices. This may cause pod scheduling issues and device allocation failures.

Troubleshooting

Operator Pod Not Starting

If the operator pod fails to start:

1. Check pod logs via OtterScale UI:

   • Navigate to Application → Workloads
   • Find the aidaptivcache-operator workload
   • Click on the pod name to view details
   • Click the Logs tab to view container logs

2. Verify node labels and taints allow the operator to schedule

3. Check that the cluster has sufficient resources

Next Steps

After successfully installing the aiDAPTIVCache Operator, you can:

• Deploy fine-tuning jobs that utilize aiDAPTIVCache devices (see Deploy aiDAPTIVCache Finetune)
• Deploy inference services with aiDAPTIVCache acceleration (see Deploy aiDAPTIVCache Inference)

Tip

When requesting aiDAPTIVCache devices in your workloads, use the resource key phison.com/ai100 in both requests and limits sections of your pod specifications.