Commit graph

458 commits

Author SHA1 Message Date
sirius0xdev
f268a83663
Update kustomization.yaml 2026-04-29 00:35:46 -04:00
sirius0xdev
9ea9d08f2d
Merge pull request #64 from sirius0xdev/feat/optimize-rtx6000-vllm-keda-scaling
feat: optimize RTX6000 vLLM KEDA scaling
2026-04-29 00:18:40 -04:00
sirius0xdev
7e7b7d414d fix: restrict KEDA scaling to /v1/(chat/)?completions paths only
- Switch to HTTPScaledObject (matches a100 pattern)
- Probes (/health, /v1/models) now ignored for scaling
- Keeps fast polling (10s), quick cooldown (30s), 15min idle scale-to-0

Health/readiness/startup probes hit pod IP directly (bypass service), so never triggered scaling anyway — but paths ensure only inference traffic scales.
2026-04-29 04:14:46 +00:00
sirius0xdev
d08bf5844a feat: optimize RTX6000 vLLM KEDA scaling
- Rename deployment to rtx6000-brain-vllm to match scaler target ref
- Set deployment replicas to 0 (KEDA controlled)
- Add pollingInterval: 10s and cooldownPeriod: 30s for faster response

This enables scale-to-zero when idle and quick scale-up on first request.

See https://github.com/sirius0xdev/gcloud-lab/tree/master/infrastructure%2Fgpus%2Fbase
2026-04-29 04:12:36 +00:00
sirius0xdev
64eaeef931
Update keda-vllm.yaml 2026-04-29 00:05:09 -04:00
sirius0xdev
d3bea19f41
Update keda-vllm.yaml 2026-04-28 23:58:26 -04:00
sirius0xdev
5622e6c49c
Update rtx6000-vllm.yaml 2026-04-28 23:55:29 -04:00
sirius0xdev
12acba27d7
Update kustomization.yaml 2026-04-28 23:51:19 -04:00
sirius0xdev
7b33f57cab add storage class 2026-04-29 02:07:21 +00:00
sirius0xdev
79942eeb5e fix disk type 2026-04-29 00:04:47 +00:00
sirius0xdev
c2f42f067d Merge branch 'master' of github.com:sirius0xdev/gcloud-lab
C
jk#
2026-04-28 23:17:01 +00:00
sirius0xdev
bb7dcd5651 fix node selector for 6000pro 2026-04-28 23:16:51 +00:00
sirius0xdev
94811c019d
Update route.yaml 2026-04-28 13:18:34 -04:00
sirius0xdev
d9048a7014 remove hostname from gateway 2026-04-28 05:00:57 +00:00
sirius0xdev
d309141ea1 fix health check 2026-04-28 04:49:09 +00:00
sirius0xdev
d61f2a2e3b health check for paaas 2026-04-28 04:44:20 +00:00
sirius0xdev
205c43f7c2 add health check for paaas 2026-04-28 04:42:42 +00:00
sirius0xdev
aca1298f64 fix route 2026-04-28 04:30:14 +00:00
sirius0xdev
3c233b0916 fix hostname 2026-04-28 04:18:33 +00:00
sirius0xdev
e9e2e02a34 fix certs apigateway 2026-04-28 04:16:38 +00:00
sirius0xdev
f2d1badae4 fix typo 2026-04-28 04:07:36 +00:00
sirius0xdev
fc44f9128c fix gateway 2026-04-28 04:00:33 +00:00
sirius0xdev
7d50abc1a1 fix kustomization 2026-04-28 03:40:54 +00:00
sirius0xdev
dc285d26a8 fix kustomization 2026-04-28 03:38:08 +00:00
sirius0xdev
cdec727963 fix kustomization file 2026-04-28 03:35:39 +00:00
sirius0xdev
b680a95d1f fix typos 2026-04-28 03:33:52 +00:00
sirius0xdev
9f5d1fb723 clean up and add routes to paas site 2026-04-28 03:31:52 +00:00
sirius0xdev
7739f2e604
Merge pull request #63 from sirius0xdev/feat/kong-ai-plugins-cilium-policy
feat: add Kong AI plugins and Cilium Local Redirect Policy
2026-04-26 23:46:03 -04:00
Hermes Agent
1df06eed96 feat: add Kong AI plugins and Cilium Local Redirect Policy
- CiliumLocalRedirectPolicy: Zero-latency Kong → vLLM on GPU nodes
- KongPlugin bundle: ai-rate-limiting (TPM), ai-prompt-guard, ai-semantic-cache, ai-failover
- Flux-integrated via kustomization.yaml
- Attach plugins to Kong routes post-deploy

Refs: LLM gateway.md optimizations.
2026-04-27 03:24:59 +00:00
sirius0xdev
6f9a260d93
Merge pull request #62 from sirius0xdev/feat/cilium-gateway-to-kong-route
feat: add HTTPRoute (cilium-gateway-to-kong-route)
2026-04-26 23:23:48 -04:00
Hermes Agent
9b62c1e6b5 feat: add HTTPRoute (cilium-gateway-to-kong-route)
- Cilium Gateway API HTTPRoute routes /v1 traffic to Kong service
- Includes placeholders for Gateway/Kong names (update post-merge)
- Added to openclaw kustomization.yaml for FluxCD sync

Refs LLM gateway.md optimizations.
2026-04-27 03:15:23 +00:00
sirius0xdev
60842d8d45
Delete alertbotSecret.yaml 2026-04-26 22:07:14 -04:00
sirius0xdev
70e9e25691
Merge pull request #60 from sirius0xdev/feat/add-trading-scripts-market-data-fetcher
feat(trading-scripts): add historical market data fetcher script
2026-04-26 19:35:44 -04:00
sirius0xdev
d2d9938994
Merge pull request #61 from sirius0xdev/feat/add-trading-scripts-readme
docs(trading-scripts): add README.md usage guide
2026-04-26 19:35:34 -04:00
Hermes Agent
51d6f7dfec docs(trading-scripts): add comprehensive README.md
- Quick start, examples, outputs
- AI integration guide
- Cron setup, troubleshooting
2026-04-26 23:34:30 +00:00
Hermes Agent
9525caf782 feat(trading-scripts): add historical market data fetcher
- 1Y+ periods with auto-interval adjustment
- Futures MultiIndex flattening + NaN dropna
- Stats: total/annual returns, volatility, drawdown
- Exports: Parquet/CSV/JSON + PNG/HTML charts
- CLI groups for stocks/futures/crypto/meme
2026-04-26 23:33:41 +00:00
sirius0xdev
cd665d3374
Update kustomization.yaml 2026-04-26 01:09:59 -04:00
sirius0xdev
cc23faf568
Update kustomization.yaml 2026-04-25 23:53:04 -04:00
sirius0xdev
08c2ce7e97
Merge pull request #58 from sirius0xdev/feat/monitoring-prometheus-grafana-tailscale
feat: add Prometheus, Grafana, and Tailscale monitoring stack
2026-04-25 22:38:25 -04:00
Hermes Agent
6183159974 feat: add Prometheus, Grafana, and Tailscale monitoring stack
- Install Prometheus + Grafana via kube-prometheus-stack (ClusterIP only, no public ingress)
- Deploy Tailscale Operator for secure VPN access to internal services
- Add CNPG/PostgreSQL monitoring dashboards
- Add vLLM inference monitoring dashboards (tokens, latency, GPU)
- Add Cilium networking dashboards (policy, traffic, drops)
- Update infra-controllers staging kustomization to include all controllers
- Add monitoring-configs Flux sync for dashboard deployment
- Update README with monitoring architecture and access instructions
- Remove broken stale monitoring files (Azure Key Vault refs, wrong domains)

Access: kubectl port-forward or Tailscale VPN (replace auth key before deploy)
2026-04-26 02:31:53 +00:00
sirius0xdev
60fcc0bd7f
Merge pull request #57 from sirius0xdev/feat/keda-path-filter
feat(keda): add path filter to HTTPScaledObject (/v1/chat/completions only)
2026-04-25 20:15:31 -04:00
Hermes Agent
01061d1b92 feat(keda): add path filter to HTTPScaledObject
Filter scales only on inference traffic (/v1/chat/completions):
- Ignores probes (/health, /v1/models)
- targetPendingRequests defaults (low queue → up)
- Keeps scaledownPeriod 900s idle zero
2026-04-25 23:58:38 +00:00
sirius0xdev
b8bf9dd242 fix deployment error 2026-04-25 23:38:36 +00:00
sirius0xdev
0a1eb2d961 bye bye openclaw 2026-04-25 23:34:07 +00:00
sirius0xdev
06123cfddf turn off keda 2026-04-25 23:33:03 +00:00
sirius0xdev
b4ffa0c238 add wellness probes to vllm and activate keda 2026-04-25 23:23:48 +00:00
sirius0xdev
ed165b9cc4 add xai to hermes 2026-04-25 21:26:54 +00:00
sirius0xdev
33570bd137 fix typo 2026-04-25 21:11:57 +00:00
sirius0xdev
b57f9a7811 activate hermes agent 2026-04-25 21:06:44 +00:00
sirius0xdev
dc1afb1472 activate hermes agent 2026-04-25 21:02:14 +00:00