Skip to content

Commit

Permalink
RHODS is now RHOAI (#83)
Browse files Browse the repository at this point in the history
  • Loading branch information
codekow authored Jun 3, 2024
1 parent a2e2ded commit be955cb
Show file tree
Hide file tree
Showing 151 changed files with 1,423 additions and 262 deletions.
8 changes: 7 additions & 1 deletion .wordlist-md
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ AmazonSageMakerFullAccess
Analytics
Ansible
ArgoCD
Authorino
Bitnami
CICD
CIDR
Expand Down Expand Up @@ -120,6 +121,7 @@ addr
adhoc
adm
ai
aiservices
alongsecret
amq
api
Expand Down Expand Up @@ -155,7 +157,6 @@ clusterissuer
clusterpolicies
clusterrolebinding
cmd
redhat-na-ssa
composable
conf
config
Expand Down Expand Up @@ -310,13 +311,15 @@ rc
rcd
rclone
redhat
redhat-na-ssa
redistributions
repo
reusability
rh
rhacs
rhdp
rhel
rhoai
rhoas
rhods
rhpds
Expand Down Expand Up @@ -370,3 +373,6 @@ wip
workspaces
www
yaml
llm
vllm
openai
17 changes: 8 additions & 9 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -23,10 +23,10 @@ In this repo, look at various [kustomized configs](components/configs) and [argo
[Red Hat Demo Platform](https://demo.redhat.com) Options (Tested)

- <a href="https://demo.redhat.com/catalog?item=babylon-catalog-prod/sandboxes-gpte.sandbox-ocp.prod&utm_source=webapp&utm_medium=share-link" target="_blank">AWS with OpenShift Open Environment</a>
- 1 x Control Plane - `m6.4xlarge`
- 0 x Workers - `m6.2xlarge`
- 1 x Control Plane - `m6a.2xlarge`
- 0 x Workers - `m6a.2xlarge`
- <a href="https://demo.redhat.com/catalog?item=babylon-catalog-prod/sandboxes-gpte.ocp4-single-node.prod&utm_source=webapp&utm_medium=share-link" target="_blank">One Node OpenShift</a>
- 1 x Control Plane - `m6.4xlarge`
- 1 x Control Plane - `m6a.2xlarge`
- <a href="https://demo.redhat.com/catalog?item=babylon-catalog-prod/community-content.com-mlops-wksp.prod&utm_source=webapp&utm_medium=share-link" target="_blank">MLOps Demo: Data Science & Edge Practice</a>

### Tools
Expand Down Expand Up @@ -59,6 +59,8 @@ git clone < repo url >

Use an [OpenShift Web Terminal](https://docs.openshift.com/container-platform/4.12/web_console/web_terminal/installing-web-terminal.html)

NOTE: Due to a bug you may need to install the web terminal operator at version 1.7 and upgrade in order for it to work correctly.

```
YOLO_URL=https://raw.githubusercontent.com/redhat-na-ssa/demo-ai-gitops-catalog/main/scripts/library/term.sh
. <(curl -s "${YOLO_URL}")
Expand All @@ -70,7 +72,7 @@ apply_firmly bootstrap/web-terminal

NOTE: open a new terminal to activate new configuration

### Cluster Quick Start for OpenShift GitOps
### Cluster Quick Start for OpenShift

Basic cluster config

Expand All @@ -92,11 +94,8 @@ Setup a demo
# setup a dev spaces demo /w gpu
apply_firmly demos/devspaces-nvidia-gpu-autoscale

# setup a rhods demo /w gpu
apply_firmly demos/rhods-nvidia-gpu-autoscale

# install all the things
apply_firmly demos/all-the-things
# setup a rhoai demo /w gpu
apply_firmly demos/rhoai-nvidia-gpu-autoscale
```

Setup an ArgoCD managed cluster
Expand Down
28 changes: 28 additions & 0 deletions components/configs/kustomized/image-puller/base/ds.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: image-puller
namespace: openshift-config
spec:
selector:
matchLabels:
name: image-puller
template:
metadata:
labels:
name: image-puller
spec:
containers:
- name: tools
image: image-registry.openshift-image-registry.svc:5000/openshift/tools:latest
command:
- tail
- -f
- /dev/null
resources:
limits:
memory: 20Mi
requests:
cpu: 10m
memory: 10Mi
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization

resources:
- overlays/default
- ds.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization

resources:
- overlays/default
- ../../base
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization

namespace: image-puller

resources:
- ../../base
- namespace.yaml

patches:
- target:
group: apps
kind: DaemonSet
name: image-puller
patch: |-
- op: add
path: /spec/template/spec/containers
value:
- name: large-app
image: 'quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-app:2.1.2'
command:
- sleep
- infinity
resources:
limits:
memory: 20Mi
requests:
cpu: 10m
memory: 10Mi
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
---
apiVersion: v1
kind: Namespace
metadata:
name: image-puller
annotations:
openshift.io/display-name: "Cache Images on Nodes"
Original file line number Diff line number Diff line change
Expand Up @@ -12,10 +12,13 @@ roleRef:
subjects:
- kind: ServiceAccount
name: data-connection-setup
namespace: ds-group-project
namespace: ds-group
- kind: ServiceAccount
name: data-connection-setup
namespace: ds-kserve-project
namespace: ds-kserve
- kind: ServiceAccount
name: data-connection-setup
namespace: ds-modelmesh
- kind: ServiceAccount
name: data-connection-setup
namespace: openshift-adp
Original file line number Diff line number Diff line change
@@ -1,8 +1,7 @@
kind: Group
apiVersion: user.openshift.io/v1
metadata:
name: rhods-admins
name: rhoai-admins
users:
- b64:kube:admin
- admin
- opentlc-mgr
Original file line number Diff line number Diff line change
Expand Up @@ -6,17 +6,28 @@ metadata:
spec:
dashboardConfig:
enablement: true
disableDistributedWorkloads: false
disableProjects: false
disableBiasMetrics: false
disableSupport: false
disablePipelines: false
disableProjectSharing: false
disableModelServing: false
disableKServe: false
disableAcceleratorProfiles: false
disableCustomServingRuntimes: false
disableModelMesh: false
disableKServeAuth: false
disableISVBadges: false
disableInfo: false
disableClusterManager: false
disablePerformanceMetrics: false
disableBYONImageStream: false
disableModelRegistry: true
disableTracking: false
groupsConfig:
adminGroups: 'rhods-admins,workshop-admins'
allowedGroups: 'system:authenticated,rhods-users'
adminGroups: rhoai-admins
allowedGroups: 'rhoai-users,system:authenticated'
modelServerSizes:
- name: Small
resources:
Expand Down Expand Up @@ -45,11 +56,13 @@ spec:
notebookController:
enabled: true
notebookNamespace: rhods-notebooks
notebookTolerationSettings:
enabled: false
key: NotebooksOnly
pvcSize: 10Gi
# gpuSetting: '4'
notebookSizes:
# kludge: everyone picks the largest, why offer more than one?
- name: "Demo / Workshop"
- name: Demo / Workshop
resources:
limits:
cpu: '6'
Expand Down Expand Up @@ -81,11 +94,11 @@ spec:
# requests:
# cpu: '7'
# memory: 56Gi
- name: X Large
resources:
limits:
cpu: '40'
memory: 186Gi
requests:
cpu: '30'
memory: 120Gi
# - name: X Large
# resources:
# limits:
# cpu: '40'
# memory: 186Gi
# requests:
# cpu: '30'
# memory: 120Gi
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
kind: Group
apiVersion: user.openshift.io/v1
metadata:
name: rhods-users
name: rhoai-users
users: []
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization

resources:
- overlays/group-project
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization

namespace: ds-group-project
namespace: ds-group

resources:
- ../../base
Expand All @@ -14,4 +14,4 @@ patches:
patch: |-
- op: add
path: /subjects/0/namespace
value: ds-group-project
value: ds-group
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization

namespace: ds-kserve-project
namespace: ds-kserve

resources:
- ../../base
Expand All @@ -14,4 +14,4 @@ patches:
patch: |-
- op: add
path: /subjects/0/namespace
value: ds-kserve-project
value: ds-kserve
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization

namespace: ds-modelmesh

resources:
- ../../base

patches:
- target:
group: rbac.authorization.k8s.io
version: v1
kind: RoleBinding
patch: |-
- op: add
path: /subjects/0/namespace
value: ds-modelmesh
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
kind: Secret
apiVersion: v1
metadata:
name: rhel-subscription-secret
namespace: redhat-ods-applications
stringData:
USERNAME: user
PASSWORD: pass
type: Opaque
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization

namespace: ds-group-project
namespace: ds-group

resources:
- model-caikit.yaml
Expand Down
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization

namespace: ds-kserve-project
namespace: ds-kserve

resources:
- caikit-tgis
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -4,4 +4,4 @@ kind: Kustomization
namespace: redhat-ods-applications

resources:
- triton
- triton-runtime.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ kind: Template
metadata:
annotations:
opendatahub.io/template-enabled: "true"
tags: triton-23.05,servingruntime
tags: triton-24.05,servingruntime
argocd.argoproj.io/sync-wave: "2"
description: Nvidia Triton Inference Server Runtime Definition
labels:
Expand Down Expand Up @@ -56,7 +56,7 @@ objects:
sizeLimit: 2Gi
containers:
- name: triton
image: nvcr.io/nvidia/tritonserver:23.05-py3
image: nvcr.io/nvidia/tritonserver:24.05-py3
command:
- /bin/sh
- -c
Expand Down
Loading

0 comments on commit be955cb

Please sign in to comment.