Skip to content

chore(llm-slo-decision-gen): bump slo-api to 0.3.0 #97

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.

Sign up for GitHub

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
remotego merged 1 commit into from
Nov 2, 2026
Merged

chore(llm-slo-decision-gen): bump slo-api to 0.3.0 #97

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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-slo-decision-gen/Chart.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ description: |
separate chart (llmscaleoperator / llmscaleoperator-system). Deploy
that one first if you need autoscaling, not just SLO storage.
type: application
version: 0.3.7
version: 0.3.8
# Matches decisionGen.image.tag (4pdosc/llm-scaler-decision-gen:0.8.0), the
# first release that understands the pdengine bound type this chart's CRD
# carries and reads DisaggregatedSets (granted in the ClusterRole).
Expand Down
4 changes: 2 additions & 2 deletions charts/llm-slo-decision-gen/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ DNS is `http://decision-gen.<namespace>.svc:80` for
|---|---|
| `decision-gen` Deployment/Service/SA | Stable recommendation endpoint |
| `decision-gen-unstable` (optional) | Same image + `LOG_LEVEL=DEBUG`; off by default |
| `slo-api` (optional) | **Leave disabled** — published `v0.1` still targets the old API group |
| `slo-api` Deployment/Service/SA/Secret | HTTP API for editing SLO specs by route; on by default (`sloApi.enabled`) |
| CRDs `LLMSLORequirement`, `JobSLORequirement` | Under `inference.modelsphere.dev`; annotated `helm.sh/resource-policy: keep` |

This chart does **not** create or patch Namespace resources. Create the target
Expand Down Expand Up @@ -64,4 +64,4 @@ Upgrading from chart `<0.3.0` replaces the old bare `decision-gen` /
| Component | Default image |
|---|---|
| decision-gen | `4pdosc/llm-scaler-decision-gen:0.8.0` (matches `appVersion`) |
| slo-api | `4pdosc/llm-slo-api:v0.1` (incompatible with current CRDs — do not enable) |
| slo-api | `4pdosc/llm-slo-api:0.3.0` |
6 changes: 4 additions & 2 deletions charts/llm-slo-decision-gen/values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,14 +78,16 @@ decisionGen:
#
# The image must be 0.2.0 or newer: v0.1 looks for LLMSLORequirement under
# inference.x-k8s.io only, and would find nothing on a cluster that has
# migrated. 0.2.0 asks the API server which group it serves.
# migrated. 0.2.0 asks the API server which group it serves. 0.3.0 adds
# JobSLORequirement routes (granted in the ClusterRole), the pdengine bound
# type and bound value 0, all of which this chart's CRDs allow.
# ---------------------------------------------------------------------------
sloApi:
enabled: true
replicas: 1
image:
repository: 4pdosc/llm-slo-api
tag: "0.2.0"
tag: "0.3.0"
pullPolicy: IfNotPresent
service:
port: 80
Expand Down
Loading