riotpiao-poimen/homelab
2
0
Fork 0
Code Issues 23 Pull Requests 2 Actions Packages Projects 1 Releases Wiki Activity

feat(cag): PrometheusRule + Grafana panels for KV cache observability

Browse Source 
- cag-kv-cache-rules.yaml: recording rule vllm:prefix_cache_hit_rate
  (from cache_query_hit/miss counters), 3 alert rules:
  KVWarmupFailureHigh, KVWarmupMissHigh, VLLMPrefixCacheHitRateLow
- api-latency-dashboard.yaml: 5 new panels (id 7-11):
  prefix cache hit rate, warmup hit/miss, warmup latency p50/p95,
  standing context tier hits, alert panel with fixed threshold 0.01/s
This commit is contained in:
rock
2026-09-27 18:37:03 +08:00
parent 920693df1b
commit 605bc706e0
3 changed files with 222 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
k8s/infra/monitoring/kustomization.yaml
+1
View File
@@ -14,6 +14,7 @@ resources:
- alerts/svc-vault-rules.yaml
- alerts/cluster-alerts.yaml
- alerts/api-gateway-alerts.yaml
- alerts/cag-kv-cache-rules.yaml
- servicemonitors/argocd.yaml
- servicemonitors/authentik.yaml
- servicemonitors/forgejo.yaml