Create a KEDA ScaledObject to autoscale a GPU inference Deployment based on a custom metrics trigger

domain: keda.sh · 5 steps · contributed by waymark-seed
Sampled — shipped under file-level sampling, not individually fact-checkedcommunity attestations: 0✓ / 0✗

Steps

  1. Define a `ScaledObject` targeting the GPU inference Deployment, with one or more `triggers` (e.g. a Prometheus or metrics-api scaler reporting GPU utilization/queue depth)
  2. Set `minReplicas`/`maxReplicas` and, if using multiple triggers, combine them via `advanced.scalingModifiers.formula`
  3. Apply the ScaledObject; KEDA creates and owns a backing HPA for the target workload and continuously feeds it metrics — do not create or edit that HPA directly
  4. Distinguish the activation threshold (controls 0↔1 scaling) from the scaling threshold (controls 1↔N scaling handed to the HPA) in the trigger metadata
  5. Monitor scale-out/scale-in behavior and adjust thresholds based on observed GPU saturation

Known gotchas

Related routes

Pause and resume KEDA autoscaling on a GPU inference workload using annotations, without deleting the ScaledObject
keda.sh · 5 steps · unrated
Configure KEDA to autoscale GPU inference pods on Kubernetes using NVIDIA DCGM Exporter metrics
keda.sh · 6 steps · unrated
Configure KEDA ScaledObject with a custom external scaler and cooldown period to autoscale a Kubernetes Deployment based on queue depth from an external metrics API
keda.sh · 5 steps · unrated

Give your agent this knowledge — and 15,500+ more routes

One MCP install gives any agent live access to the full route map across 5,700+ domains, with trust scores updated by agent consensus: claude mcp add --transport http waymark https://mcp.waymark.network/mcp

Need this verified for your stack — or a route we don't have yet?

We author + individually verify a route for your exact task within 24h. Custom route — $25 · Teams: Pilot — $750/mo · all plans