mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +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" />
80 lines
2.1 KiB
Text
80 lines
2.1 KiB
Text
apiVersion: v1
|
|
kind: PersistentVolumeClaim
|
|
metadata:
|
|
name: llama-pvc
|
|
spec:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
resources:
|
|
requests:
|
|
storage: 1Gi
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: llama-stack-server
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: llama-stack
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: llama-stack
|
|
spec:
|
|
containers:
|
|
- name: llama-stack
|
|
image: llamastack/distribution-remote-vllm:latest
|
|
imagePullPolicy: Always # since we have specified latest instead of a version
|
|
env:
|
|
- name: ENABLE_CHROMADB
|
|
value: "true"
|
|
- name: CHROMADB_URL
|
|
value: http://chromadb.default.svc.cluster.local:6000
|
|
- name: VLLM_URL
|
|
value: http://vllm-server.default.svc.cluster.local:8000/v1
|
|
- name: VLLM_MAX_TOKENS
|
|
value: "3072"
|
|
- name: VLLM_SAFETY_URL
|
|
value: http://vllm-server-safety.default.svc.cluster.local:8001/v1
|
|
- name: POSTGRES_HOST
|
|
value: postgres-server.default.svc.cluster.local
|
|
- name: POSTGRES_PORT
|
|
value: "5432"
|
|
- name: VLLM_TLS_VERIFY
|
|
value: "false"
|
|
- name: INFERENCE_MODEL
|
|
value: "${INFERENCE_MODEL}"
|
|
- name: SAFETY_MODEL
|
|
value: "${SAFETY_MODEL}"
|
|
- name: TAVILY_SEARCH_API_KEY
|
|
value: "${TAVILY_SEARCH_API_KEY}"
|
|
command: ["python", "-m", "llama_stack.distribution.server.server", "--config", "/etc/config/stack_run_config.yaml", "--port", "8321"]
|
|
ports:
|
|
- containerPort: 8321
|
|
volumeMounts:
|
|
- name: llama-storage
|
|
mountPath: /root/.llama
|
|
- name: llama-config
|
|
mountPath: /etc/config
|
|
volumes:
|
|
- name: llama-storage
|
|
persistentVolumeClaim:
|
|
claimName: llama-pvc
|
|
- name: llama-config
|
|
configMap:
|
|
name: llama-stack-config
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: llama-stack-service
|
|
spec:
|
|
selector:
|
|
app.kubernetes.io/name: llama-stack
|
|
ports:
|
|
- protocol: TCP
|
|
port: 8321
|
|
targetPort: 8321
|
|
type: ClusterIP
|