Skip to content

Commit f8bed11

Browse files
committed
fix: add scaling adapter
Signed-off-by: Julien Mancuso <[email protected]>
1 parent 66fddab commit f8bed11

File tree

1 file changed

+13
-4
lines changed

1 file changed

+13
-4
lines changed

docs/kubernetes/autoscaling.md

Lines changed: 13 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -527,14 +527,23 @@ spec:
527527

528528
## Manual Scaling
529529

530-
You can manually scale a service by patching the adapter:
530+
You can manually scale a service using the scale subresource:
531531

532532
```bash
533-
kubectl patch dgdsa sglang-agg-decode -n default \
534-
--type='json' -p='[{"op": "replace", "path": "/spec/replicas", "value": 3}]'
533+
kubectl scale dgdsa sglang-agg-decode -n default --replicas=3
535534
```
536535

537-
> **Note**: If an autoscaler is managing the adapter, your change will be overwritten on the next evaluation cycle.
536+
Verify the scaling:
537+
538+
```bash
539+
kubectl get dgdsa sglang-agg-decode -n default
540+
541+
# Output:
542+
# NAME DGD SERVICE REPLICAS AGE
543+
# sglang-agg-decode sglang-agg decode 3 10m
544+
```
545+
546+
> **Note**: If an autoscaler (KEDA, HPA, Planner) is managing the adapter, your change will be overwritten on the next evaluation cycle.
538547

539548
## Best Practices
540549

0 commit comments

Comments
 (0)