manifests/inference.yaml

# * Copyright 2022 Google LLC
# *
# * Licensed under the Apache License, Version 2.0 (the "License");
# * you may not use this file except in compliance with the License.
# * You may obtain a copy of the License at
# *
# *      http://www.apache.org/licenses/LICENSE-2.0
# *
# * Unless required by applicable law or agreed to in writing, software
# * distributed under the License is distributed on an "AS IS" BASIS,
# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# * See the License for the specific language governing permissions and
# * limitations under the License.

apiVersion: apps/v1
kind: Deployment
metadata:
  name: inference-deployment
  namespace: airflow
spec:
  replicas: 1
  selector:
    matchLabels:
      app: gemma-server
  template:
    metadata:
      labels:
        app: gemma-server
        ai.gke.io/model: gemma-2-9b-it
        ai.gke.io/inference-server: vllm
      annotations:
        gke-gcsfuse/volumes: "true"
    spec:
      serviceAccountName: airflow-mlops-sa
      tolerations:
      - key: "nvidia.com/gpu"
        operator: "Exists"
        effect: "NoSchedule"
      - key: "on-demand"
        value: "true"
        operator: "Equal"
        effect: "NoSchedule"
      containers:
      - name: inference-server
        image: vllm/vllm-openai:latest
        ports:
        - containerPort: 8000
        resources:
          requests:
            nvidia.com/gpu: "2"
          limits:
            nvidia.com/gpu: "2"
        command: ["/bin/sh", "-c"]
        args:
        - |
          python3 -m vllm.entrypoints.api_server --model=/modeldata/fine_tuned_model --tokenizer=/modeldata/fine_tuned_model --tensor-parallel-size=2
        volumeMounts:
        - mountPath: /dev/shm
          name: dshm
        - name: gcs-fuse-csi-ephemeral
          mountPath: /modeldata
          readOnly: true
      volumes:
      - name: dshm
        emptyDir:
          medium: Memory
      - name: gcs-fuse-csi-ephemeral
        csi:
          driver: gcsfuse.csi.storage.gke.io
          volumeAttributes:
            bucketName: BUCKET_DATA_NAME
            mountOptions: "implicit-dirs,file-cache:enable-parallel-downloads:true,file-cache:max-parallel-downloads:-1"
            fileCacheCapacity: "20Gi"
            fileCacheForRangeRead: "true"
            metadataStatCacheCapacity: "-1"
            metadataTypeCacheCapacity: "-1"
            metadataCacheTTLSeconds: "-1"
      nodeSelector:
        cloud.google.com/gke-accelerator: nvidia-l4