- 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. |
||
|---|---|---|
| .. | ||
| cilium-local-redirect.yaml | ||
| kong-plugins.yaml | ||