63 lines
2.1 KiB
YAML
63 lines
2.1 KiB
YAML
|
# NetworkPolicy for LLM inference engines (llm-serving namespace).
|
||
|
|
#
|
||
|
|
# These pods have NO auth — vLLM, Ollama, and TEI accept any request.
|
||
|
|
# All access MUST go through the api-gateway, which validates JWTs and
|
||
|
|
# injects identity headers (X-Forwarded-User, X-Auth-Verified).
|
||
|
|
#
|
||
|
|
# Replaces the hand-applied llm-serving-default-deny policy that used
|
||
|
|
# `llm-client: "true"` pod label as a selector — any pod in any namespace
|
||
|
|
# could self-grant access by adding that label, which defeats the purpose.
|
||
|
|
#
|
||
|
|
# This policy restricts ingress to:
|
||
|
|
# 1. api namespace (gateway) — the sole entry point for inference
|
||
|
|
# 2. monitoring namespace — Prometheus scraping vLLM/TEI /metrics
|
||
|
|
# 3. intra-namespace — pod-to-pod (future: multi-replica comms)
|
||
|
|
apiVersion: networking.k8s.io/v1
|
||
|
|
kind: NetworkPolicy
|
||
|
|
metadata:
|
||
|
|
name: llm-serving-ingress
|
||
|
|
namespace: llm-serving
|
||
|
|
labels:
|
||
|
|
app.kubernetes.io/part-of: llm-serving
|
||
|
|
spec:
|
||
|
|
podSelector:
|
||
|
|
matchLabels:
|
||
|
|
app.kubernetes.io/part-of: llm-serving
|
||
|
|
policyTypes:
|
||
|
|
- Ingress
|
||
|
|
ingress:
|
||
|
|
# Allow from api-gateway (namespace: api)
|
||
|
|
# Gateway proxies /v1/chat/completions, /v1/embeddings, /v1/rerank
|
||
|
|
- from:
|
||
|
|
- namespaceSelector:
|
||
|
|
matchLabels:
|
||
|
|
kubernetes.io/metadata.name: api
|
||
|
|
ports:
|
||
|
|
- protocol: TCP
|
||
|
|
port: 8080 # vLLM, Ollama HTTP
|
||
|
|
- protocol: TCP
|
||
|
|
port: 80 # KServe predictor services
|
||
|
|
- protocol: TCP
|
||
|
|
port: 8000 # vLLM direct (some configs)
|
||
|
|
- protocol: TCP
|
||
|
|
port: 11434 # Ollama native port
|
||
|
|
# Allow Prometheus scraping from monitoring namespace
|
||
|
|
# vLLM: :8080/metrics, TEI: :9000/metrics
|
||
|
|
- from:
|
||
|
|
- namespaceSelector:
|
||
|
|
matchLabels:
|
||
|
|
kubernetes.io/metadata.name: monitoring
|
||
|
|
ports:
|
||
|
|
- protocol: TCP
|
||
|
|
port: 8080
|
||
|
|
- protocol: TCP
|
||
|
|
port: 9000
|
||
|
|
# Allow intra-namespace (pod-to-pod within llm-serving)
|
||
|
|
- from:
|
||
|
|
- podSelector:
|
||
|
|
matchLabels:
|
||
|
|
app.kubernetes.io/part-of: llm-serving
|
||
|
|
ports:
|
||
|
|
- protocol: TCP
|
||
|
|
port: 8080
|