deployment.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: tei-deployment
spec:
  replicas: 1
  selector:
    matchLabels:
      app: tei-server
  template:
    metadata:
      labels:
        app: tei-server
        hf.co/model: Snowflake--snowflake-arctic-embed-m
        hf.co/task: text-embeddings
    spec:
      containers:
        - name: tei-container
          image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-embeddings-inference-cpu.1-4:latest
          resources:
            requests:
              cpu: "8"
              memory: "32Gi"
            limits:
              cpu: "16"
              memory: "64Gi"
          env:
            - name: MODEL_ID
              value: Snowflake/snowflake-arctic-embed-m
            - name: NUM_SHARD
              value: "1"
            - name: PORT
              value: "8080"
          volumeMounts:
            - mountPath: /data
              name: data
      volumes:
        - name: data
          emptyDir: {}
      nodeSelector:
        cloud.google.com/compute-class: "Performance"
        cloud.google.com/machine-family: "c2"