mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
7fb4bdabea
This Kubernetes cluster has: - vLLM for serving an inference model - vLLM for serving a safety model - Postgres DB (for metadata and other state for the Llama Stack distro) - Chroma DB for Vector IO (memory) Perhaps most importantly, this was me trying to learn Kubernetes for the first time. ## Test Plan Run `sh apply.sh` against an EKS cluster, then after `kubectl port-forward service/llama-stack-service 8321:8321` and after many attempts, we have finally: <img width="1589" alt="image" src="https://github.com/user-attachments/assets/c69f242d-6aaa-4def-9f7c-172113b8bfc1" /> <img width="1978" alt="image" src="https://github.com/user-attachments/assets/cf678404-f551-4fa5-9077-bebe3e8e8ae8" />
66 lines
1.4 KiB
Text
66 lines
1.4 KiB
Text
apiVersion: v1
|
|
kind: PersistentVolumeClaim
|
|
metadata:
|
|
name: postgres-pvc
|
|
spec:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
resources:
|
|
requests:
|
|
storage: 10Gi
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: postgres
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: postgres
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: postgres
|
|
spec:
|
|
containers:
|
|
- name: postgres
|
|
image: postgres:15
|
|
env:
|
|
- name: POSTGRES_DB
|
|
value: "${POSTGRES_DB}"
|
|
- name: POSTGRES_USER
|
|
value: "${POSTGRES_USER}"
|
|
- name: POSTGRES_PASSWORD
|
|
value: "${POSTGRES_PASSWORD}"
|
|
- name: PGDATA
|
|
value: "/var/lib/postgresql/data/pgdata"
|
|
ports:
|
|
- containerPort: 5432
|
|
resources:
|
|
requests:
|
|
memory: "512Mi"
|
|
cpu: "250m"
|
|
limits:
|
|
memory: "1Gi"
|
|
cpu: "500m"
|
|
volumeMounts:
|
|
- name: postgres-storage
|
|
mountPath: /var/lib/postgresql/data
|
|
volumes:
|
|
- name: postgres-storage
|
|
persistentVolumeClaim:
|
|
claimName: postgres-pvc
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: postgres-server
|
|
spec:
|
|
selector:
|
|
app.kubernetes.io/name: postgres
|
|
ports:
|
|
- protocol: TCP
|
|
port: 5432
|
|
targetPort: 5432
|
|
type: ClusterIP
|