llm-d/llm-d-workload-variant-autoscaler

Flaky e2e test: "should recommend scale-down when load drops below scaleDownBoundary" (saturation V2 smoke) about 2 months ago

bug help wanted area/ci

47

Variant optimization autoscaler for distributed inference workloads

Go

EPIC: document existing e2es and extend e2es to close gaps 2 months ago

help wanted triage/accepted lifecycle/rotten

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Add more tests for saturation v1 (percentage threshold) 2 months ago

help wanted triage/accepted lifecycle/rotten

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Add model based e2es (SLO based) 2 months ago

help wanted triage/accepted lifecycle/rotten

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

e2e: limit/remove Ensure* helpers to avoid cross-test resource mutation illusion 2 months ago

good first issue pickedup triage/accepted lifecycle/rotten

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Reduce log pollution during e2e tests from deprecation warnings 3 months ago

good first issue e2e passing needs-triage

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

acceleratorName label requirement on VariantAutoscaling is not documented 3 months ago

good first issue triage/accepted lifecycle/rotten

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

E2E deploy depends on the llm-d/llm-d repo, creating a circular dependency during release 3 months ago

help wanted area/ci

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Annotation mode reads GetHPAMinReplicas() instead of minReplicaCount 3 months ago

good first issue triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

`config/manager/kustomization.yaml` pins image tag to v0.5.1 at the v0.7.0 release tag 3 months ago

bug good first issue triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

ValidateTLSConfig unconditionally rejects http:// Prometheus URLs — no way to opt out 3 months ago

good first issue triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Upgrade: e2e test 3 months ago

help wanted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Remove hardcoding of analyzer mode 5 months ago

good first issue

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Change VA CRD group to llm-d.ai 5 months ago

good first issue triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Restrict WVA controller ClusterRole to only WVA ConfigMaps 6 months ago

bug good first issue triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Add saturation v2 (token based) e2es 6 months ago

help wanted triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

bug: the CI/CD linter does not work as expected 6 months ago

bug good first issue area/ci

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Fix PodScrapingSource to support fetching individual metrics 7 months ago

bug enhancement good first issue triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Evaluate the need for `EscapePromQLValue` func 7 months ago

good first issue triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Cleanup model based code 7 months ago

good first issue triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Evaluate and cleanup interfaces folder 7 months ago

good first issue triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

bug: make test fails when helm is not installed 7 months ago

good first issue triage/accepted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

Align repository with llm-d repo template (9 items) 7 months ago

good first issue help wanted

llm-d/llm-d-workload-variant-autoscaler

47

Variant optimization autoscaler for distributed inference workloads

Go

llm-d/llm-d-workload-variant-autoscaler

Open Issues Need Help