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" />
71 lines
1.6 KiB
Text
71 lines
1.6 KiB
Text
apiVersion: v1
|
|
kind: PersistentVolumeClaim
|
|
metadata:
|
|
name: vllm-models
|
|
spec:
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
volumeMode: Filesystem
|
|
resources:
|
|
requests:
|
|
storage: 50Gi
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: vllm-server
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: vllm
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: vllm
|
|
workload-type: inference
|
|
spec:
|
|
affinity:
|
|
podAntiAffinity:
|
|
requiredDuringSchedulingIgnoredDuringExecution:
|
|
- labelSelector:
|
|
matchExpressions:
|
|
- key: workload-type
|
|
operator: In
|
|
values:
|
|
- inference
|
|
topologyKey: kubernetes.io/hostname # Ensures no two inference pods on same node
|
|
containers:
|
|
- name: vllm
|
|
image: vllm/vllm-openai:latest
|
|
command: ["/bin/sh", "-c"]
|
|
args:
|
|
- "vllm serve ${INFERENCE_MODEL} --dtype float16 --enforce-eager --max-model-len 4096 --gpu-memory-utilization 0.6"
|
|
env:
|
|
- name: HUGGING_FACE_HUB_TOKEN
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: hf-token-secret
|
|
key: token
|
|
ports:
|
|
- containerPort: 8000
|
|
volumeMounts:
|
|
- name: llama-storage
|
|
mountPath: /root/.cache/huggingface
|
|
volumes:
|
|
- name: llama-storage
|
|
persistentVolumeClaim:
|
|
claimName: vllm-models
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: vllm-server
|
|
spec:
|
|
selector:
|
|
app.kubernetes.io/name: vllm
|
|
ports:
|
|
- protocol: TCP
|
|
port: 8000
|
|
targetPort: 8000
|
|
type: ClusterIP
|