diff --git a/charts/llm-slo-decision-gen/Chart.yaml b/charts/llm-slo-decision-gen/Chart.yaml index 34d2d40..3b61822 100644 --- a/charts/llm-slo-decision-gen/Chart.yaml +++ b/charts/llm-slo-decision-gen/Chart.yaml @@ -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). diff --git a/charts/llm-slo-decision-gen/README.md b/charts/llm-slo-decision-gen/README.md index cb843c0..738ee6d 100644 --- a/charts/llm-slo-decision-gen/README.md +++ b/charts/llm-slo-decision-gen/README.md @@ -17,7 +17,7 @@ DNS is `http://decision-gen..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 @@ -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` | diff --git a/charts/llm-slo-decision-gen/values.yaml b/charts/llm-slo-decision-gen/values.yaml index 5117f60..0b84d08 100644 --- a/charts/llm-slo-decision-gen/values.yaml +++ b/charts/llm-slo-decision-gen/values.yaml @@ -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