models:
- name: gpt-oss-20b
displayName: OpenAI gpt-oss-20b
uri: oci://registry.redhat.io/rhelai1/modelcar-gpt-oss-20b:1.5
resources:
limits:
cpu: "4"
memory: 24Gi
nvidia.com/gpu: "1"
requests:
cpu: "2"
memory: 16Gi
nvidia.com/gpu: "1"
extraArgs:
- --enable-force-include-usage
tolerations:
- effect: NoSchedule
key: nvidia.com/gpu
operator: ExistsCustomizing the MaaS Code Assistant AI Quickstart pattern
This pattern deploys an AI code assistant with tiered user access, rate limiting, and NVIDIA Nemotron model serving. You can customize the models, rate limit policies, user tiers, and IDE configuration.
Changing models
The pattern serves two models by default:
nemotron-3-nano-30b-a3b-fp8— Available to premium and enterprise tier users.gpt-oss-20b— Available to all user tiers.
To change or add models, edit the models list in overrides/maas-quickstart.yaml. The pattern pulls models from OCI registries and does not require a HuggingFace API token.
The model definitions specify the model URI, resource requirements, GPU tolerations, and vLLM arguments. For example:
Each model requires a GPU with at least 48 GB of VRAM. Adding models beyond the default two requires additional GPU nodes. |
Adjusting rate limits and user tiers
The pattern uses Kuadrant (Red Hat Connectivity Link) to enforce per-tier rate limits on inference requests. The default tiers and limits are:
| Tier | Rate limit | Description |
|---|---|---|
Free | 5 requests per 2 minutes | Basic access for evaluation |
Premium | 20 requests per 2 minutes | Standard production usage |
Enterprise | 50 requests per 2 minutes | High-throughput workloads |
To adjust rate limits, modify the tiers section in overrides/maas-quickstart.yaml. The following example increases the premium tier request limit to 40 and the token limit to 20000:
tiers:
premium:
users:
- premium-user
requestRates:
- limit: 40
window: 2m
tokenRates:
- limit: 20000
window: 1mPush your changes to your forked repository so the GitOps framework applies the updated configuration.
Managing users
htpasswd with OpenShift OAuth handles user authentication. The default users are:
admin— Full administrative access (enterprise tier)free-user— Free tier accesspremium-user— Premium tier accessenterprise-user— Enterprise tier access
HashiCorp Vault and the External Secrets Operator store and manage user passwords in the values-secret.yaml file. To change a user password after initial deployment, update the secret value in your values-secret.yaml file and redeploy the pattern.
To assign users to different tiers, modify the tiers section in overrides/maas-quickstart.yaml:
tiers:
free:
users:
- free-user
premium:
users:
- premium-user
- user1
enterprise:
users:
- admin
- enterprise-userConfiguring OpenShift DevSpaces
The pattern integrates the Continue AI extension in OpenShift DevSpaces to provide code assistance directly in the IDE. DevSpaces is preconfigured to clone the AI Quickstart repository and connect to the vLLM inference endpoints.
To customize the DevSpaces configuration, you can adjust:
Default IDE settings and extensions
Resource limits for developer workspaces
The inference endpoint URL used by the Continue extension
Provisioning GPU nodes
This pattern requires at least 2 NVIDIA GPU nodes with 48 GB or more of VRAM each. On AWS, the pattern automatically provisions g6e.2xlarge GPU machine sets with NVIDIA L40S GPUs.
If your cluster does not have GPU nodes, you must add them before you deploy the pattern. The pattern installs all required operators, including the NVIDIA GPU Operator, automatically during deployment.
