Skip to content

Add scheduler plugins helm chart #17

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 3, 2025

Conversation

carlory
Copy link
Member

@carlory carlory commented May 29, 2025

Test:

(base) ➜  scheduler-plugins git:(install-as-a-second-scheduler) helm upgrade --install llmaz-scheduler --set scheduler.image.repository=ghcr.io/carlory/inftyai/scheduler-plugins --set scheduler.image.tag=latest  ./chart
Release "llmaz-scheduler" has been upgraded. Happy Helming!
NAME: llmaz-scheduler
LAST DEPLOYED: Thu May 29 18:11:25 2025
NAMESPACE: default
STATUS: deployed
REVISION: 9
TEST SUITE: None

(base) ➜  scheduler-plugins git:(install-as-a-second-scheduler) kubectl get po
NAME                                                            READY   STATUS    RESTARTS   AGE
llmaz-scheduler-6899f8dc7d-fljfj                                1/1     Running   0          8m15s

(base) ➜  scheduler-plugins git:(install-as-a-second-scheduler) kubectl get po -owide
NAME                                                            READY   STATUS    RESTARTS   AGE     IP            NODE                           NOMINATED NODE   READINESS GATES
llmaz-scheduler-6899f8dc7d-fljfj                                1/1     Running   0          9m15s   10.244.3.24   kind-worker                    <none>           <none>
qwen2-0--5b-demo-0                                              1/1     Running   0          5m50s   10.244.10.2   quirky-hofstadter-2901052955   <none>           <none>

(base) ➜  scheduler-plugins git:(install-as-a-second-scheduler) kubectl get openmodel qwen2-0--5b -oyaml
...
  inferenceConfig:
    flavors:
    - limits:
        cpu: 100m
        memory: 10Mi
      name: 0x
      nodeSelector:
        node.kubernetes.io/instance-type: c-0x-amd64-linux
    - limits:
        cpu: 100m
        memory: 10Mi
      name: 2x
      nodeSelector:
        node.kubernetes.io/instance-type: c-2x-amd64-linux
    - limits:
        cpu: 100m
        memory: 10Mi
      name: 1x
      nodeSelector:
        node.kubernetes.io/instance-type: c-1x-amd64-linux
...

(base) ➜  scheduler-plugins git:(install-as-a-second-scheduler) kubectl get po qwen2-0--5b-demo-0 -oya
ml
apiVersion: v1
kind: Pod
metadata:
  annotations:
    leaderworkerset.sigs.k8s.io/size: "1"
    llmaz.io/inference-service-flavors: 1x

(base) ➜  scheduler-plugins git:(install-as-a-second-scheduler) kubectl get nodeclaim
NAME            TYPE               CAPACITY   ZONE          NODE                           READY   AGE
default-tgf4f   c-1x-amd64-linux   spot       test-zone-a   quirky-hofstadter-2901052955   True    3h56m

@InftyAI-Agent InftyAI-Agent added needs-triage Indicates an issue or PR lacks a label and requires one. needs-priority Indicates a PR lacks a label and requires one. do-not-merge/needs-kind Indicates a PR lacks a label and requires one. labels May 29, 2025
@InftyAI-Agent InftyAI-Agent requested a review from kerthcet May 29, 2025 10:15
scheduler:
name: llmaz-scheduler
image:
repository: inftyai/scheduler-plugins
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

updated.

@carlory carlory force-pushed the install-as-a-second-scheduler branch from 776404b to 4267c3c Compare June 3, 2025 10:06
@kerthcet
Copy link
Member

kerthcet commented Jun 3, 2025

/lgtm
/approve
/kind feature

I'll merge first and will test to push a chart later.

@InftyAI-Agent InftyAI-Agent added lgtm Looks good to me, indicates that a PR is ready to be merged. approved Indicates a PR has been approved by an approver from all required OWNERS files. feature Categorizes issue or PR as related to a new feature. and removed do-not-merge/needs-kind Indicates a PR lacks a label and requires one. labels Jun 3, 2025
@InftyAI-Agent InftyAI-Agent merged commit d1a0f9c into InftyAI:main Jun 3, 2025
24 of 29 checks passed
@carlory carlory deleted the install-as-a-second-scheduler branch June 4, 2025 01:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
approved Indicates a PR has been approved by an approver from all required OWNERS files. feature Categorizes issue or PR as related to a new feature. lgtm Looks good to me, indicates that a PR is ready to be merged. needs-priority Indicates a PR lacks a label and requires one. needs-triage Indicates an issue or PR lacks a label and requires one.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants