Filter scales only on inference traffic (/v1/chat/completions): - Ignores probes (/health, /v1/models) - targetPendingRequests defaults (low queue → up) - Keeps scaledownPeriod 900s idle zero |
||
|---|---|---|
| .. | ||
| customer1 | ||
Filter scales only on inference traffic (/v1/chat/completions): - Ignores probes (/health, /v1/models) - targetPendingRequests defaults (low queue → up) - Keeps scaledownPeriod 900s idle zero |
||
|---|---|---|
| .. | ||
| customer1 | ||