Skip to content
This repository was archived by the owner on Oct 15, 2025. It is now read-only.
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion charts/llm-d/Chart.yaml
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
apiVersion: v2
name: llm-d
type: application
version: 0.0.6
version: 0.0.7
appVersion: "0.0.1"
icon: data:null
description: A Helm chart for llm-d
Expand Down
2 changes: 1 addition & 1 deletion charts/llm-d/README.md
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@

# llm-d Helm Chart for OpenShift

![Version: 0.0.6](https://img.shields.io/badge/Version-0.0.6-informational?style=flat-square)
![Version: 0.0.7](https://img.shields.io/badge/Version-0.0.7-informational?style=flat-square)
![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square)

A Helm chart for llm-d
Expand Down
49 changes: 49 additions & 0 deletions charts/llm-d/templates/modelservice/clusterRoleManager.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ rules:
- list
- watch
- create
- update
- apiGroups:
- rbac.authorization.k8s.io
resources:
Expand All @@ -46,6 +47,54 @@ rules:
- list
- watch
- create
- update
# MSV2 HACK BEGIN ---------------
- apiGroups:
- "v1"
resources:
- "secrets"
verbs:
- "get"
- "list"
- "watch"
- apiGroups:
- "inference.networking.x-k8s.io"
resources:
- "inferencepools"
- "inferencemodels"
verbs:
- "get"
- "watch"
- "list"
- apiGroups:
- ""
resources:
- "pods"
verbs:
- "get"
- "watch"
- "list"
- apiGroups:
- "discovery.k8s.io"
resources:
- "endpointslices"
verbs:
- "get"
- "watch"
- "list"
- apiGroups:
- "authentication.k8s.io"
resources:
- "tokenreviews"
verbs:
- "create"
- apiGroups:
- "authorization.k8s.io"
resources:
- "subjectaccessreviews"
verbs:
- "create"
# MSV2 HACK END ---------------
- apiGroups:
- apps
resources:
Expand Down
10 changes: 9 additions & 1 deletion charts/llm-d/templates/modelservice/deployment.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -42,8 +42,16 @@ spec:
- --metrics-bind-address=:8443
- --leader-elect=false
- --health-probe-bind-address=:8081
# MSV2 HACK BEGIN
- --epp-cluster-role
- endpoint-picker-role
- endpoint-picker-clusterrole
- --epp-pull-secrets
- endpoint-picker-pull-secret
- --pd-cluster-role
- prefill-decode-clusterrole
- --pd-pull-secrets
- prefill-decode-pull-secret
# MSV2 HACK END
command:
- /manager
image: {{ include "modelservice.image" . }}
Expand Down
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: endpoint-picker-role
name: endpoint-picker-clusterrole
rules:
- apiGroups:
- "inference.networking.x-k8s.io"
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: prefill-decode-clusterrole
rules:
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
kind: Secret
apiVersion: v1
metadata:
name: endpoint-picker-pull-secret
4 changes: 4 additions & 0 deletions charts/llm-d/templates/modelservice/ms-v2-hack/secret-pd.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
kind: Secret
apiVersion: v1
metadata:
name: pd-pull-secret
Loading