112 lines
4.0 KiB
YAML
112 lines
4.0 KiB
YAML
---
|
|
# --- OLM operators ---
|
|
# Installed in order. RHOAI is pinned to stable-3.5: the MaaS DSC layout
|
|
# (aigateway.modelsAsAService) changed between 3.4 and 3.5, so don't float on stable-3.x.
|
|
# RHCL must be 1.4.x (Kuadrant >= 1.4.2 for AuthPolicy spec.defaults.rules).
|
|
# cert-manager is a prerequisite but already installed by deploy_openshift.yml.
|
|
rhoai_maas_operators:
|
|
- name: rhcl-operator
|
|
namespace: openshift-operators
|
|
channel: stable-1.4
|
|
- name: leader-worker-set
|
|
namespace: openshift-lws-operator
|
|
channel: stable-v1.0
|
|
operator_group_target_namespaces:
|
|
- openshift-lws-operator
|
|
- name: rhods-operator
|
|
namespace: redhat-ods-operator
|
|
channel: stable-3.5
|
|
namespace_labels:
|
|
openshift.io/cluster-monitoring: "true"
|
|
rhoai_maas_wait_timeout: 900
|
|
|
|
# --- Gateway ---
|
|
# Empty = maas.<cluster ingress domain>.
|
|
rhoai_maas_hostname: ""
|
|
# The gateway gets its own single-host certificate. Don't use the *.apps wildcard:
|
|
# browsers would reuse the MaaS HTTP/2 connection for every other *.apps host
|
|
# (console, dashboards), and the MaaS gateway answers those with 404.
|
|
rhoai_maas_gateway_cert_secret: maas-gateway-tls
|
|
# cert-manager ClusterIssuer for the gateway certificate. Empty = use the existing
|
|
# rhoai_maas_gateway_cert_secret as-is and don't create a Certificate.
|
|
rhoai_maas_gateway_cert_issuer: letsencrypt-production
|
|
# No cloud LB on this cluster: run the gateway Service as ClusterIP and expose it
|
|
# through a passthrough Route on the default router. Set to LoadBalancer with MetalLB.
|
|
rhoai_maas_gateway_service_type: ClusterIP
|
|
rhoai_maas_gateway_create_route: true
|
|
|
|
# --- MaaS database ---
|
|
# PostgreSQL is provisioned by the cloudnativepg_operator role (see the playbook);
|
|
# this secret holds its credentials (type kubernetes.io/basic-auth).
|
|
rhoai_maas_db_secret_name: maas-postgres-secret
|
|
rhoai_maas_db_secret_namespace: rhoai-maas-db
|
|
rhoai_maas_db_sslmode: require
|
|
rhoai_maas_infra_namespace: redhat-ai-gateway-infra
|
|
|
|
# --- DataScienceCluster ---
|
|
# Minimal component set for MaaS. Anything not listed here is set to Removed.
|
|
rhoai_maas_dsc_name: default-dsc
|
|
rhoai_maas_dsc_managed_components:
|
|
- dashboard
|
|
- kserve
|
|
- aigateway
|
|
- ogx
|
|
rhoai_maas_dsc_removed_components:
|
|
- aipipelines
|
|
- feastoperator
|
|
- kueue
|
|
- mlflowoperator
|
|
- modelregistry
|
|
- ray
|
|
- trainer
|
|
- trainingoperator
|
|
- trustyai
|
|
- workbenches
|
|
|
|
# --- Models (ExternalModel fronting in-cluster OpenAI-compatible servers) ---
|
|
# The api_key_secret must already exist in the model namespace with key `api-key`;
|
|
# the role only labels it for MaaS. Names must not collide with existing Services
|
|
# in the namespace (the controller creates a Service per provider/model).
|
|
rhoai_maas_external_models:
|
|
- name: qwen35-9b-coder
|
|
namespace: llm-coding-assistant
|
|
display_name: Qwen3.5 9B Coder (llama.cpp)
|
|
description: Qwen3.5-9B Q5_K_M served by llama.cpp on the desktop GPU node
|
|
provider_name: llama-coder-provider
|
|
provider_type: openai
|
|
endpoint: llama-coder.llm-coding-assistant.svc.cluster.local
|
|
port: 8080
|
|
tls: false
|
|
api_key_secret: llama-coder-api-key
|
|
# llama-server serves a single model and ignores the request's model field.
|
|
target_model: Qwen3.5-9B-Q5_K_M.gguf
|
|
api_format: openai-chat
|
|
path: /v1/chat/completions
|
|
|
|
# --- Access policy and quota (CR spec shapes, models-as-a-service namespace) ---
|
|
rhoai_maas_auth_policies:
|
|
- name: llama-coder-access
|
|
display_name: llama-coder access
|
|
description: All authenticated users can call the llama-coder model
|
|
groups:
|
|
- system:authenticated
|
|
users: []
|
|
model_refs:
|
|
- name: qwen35-9b-coder
|
|
namespace: llm-coding-assistant
|
|
|
|
rhoai_maas_subscriptions:
|
|
- name: llama-coder-default
|
|
display_name: llama-coder default
|
|
description: 200k tokens/hour per user for all authenticated users
|
|
priority: 10
|
|
groups:
|
|
- system:authenticated
|
|
users: []
|
|
model_refs:
|
|
- name: qwen35-9b-coder
|
|
namespace: llm-coding-assistant
|
|
tokenRateLimits:
|
|
- limit: 200000
|
|
window: 1h
|