ai-ml/llm-serving-gemma/vllm/vllm-3-12b-it.yaml

# Copyright 2025 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.

# [START gke_ai_ml_llm_serving_gemma_vllm_3_12b_it_deployment]
apiVersion: apps/v1
kind: Deployment
metadata:
  name: vllm-gemma-deployment
spec:
  replicas: 1
  selector:
    matchLabels:
      app: gemma-server
  template:
    metadata:
      labels:
        app: gemma-server
        ai.gke.io/model: gemma-3-12b-it
        ai.gke.io/inference-server: vllm
        examples.ai.gke.io/source: user-guide
    spec:
      containers:
      - name: inference-server
        image: us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch-vllm-serve:20250312_0916_RC01
        resources:
          requests:
            cpu: "4"
            memory: "32Gi"
            ephemeral-storage: "32Gi"
            nvidia.com/gpu: "2"
          limits:
            cpu: "4"
            memory: "32Gi"
            ephemeral-storage: "32Gi"
            nvidia.com/gpu: "2"
        command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
        args:
        - --model=$(MODEL_ID)
        - --tensor-parallel-size=2
        - --host=0.0.0.0
        - --port=8000
        - --max-model-len=16384
        - --max-num-seqs=4
        env:
        - name: MODEL_ID
          value: google/gemma-3-12b-it
        - name: HUGGING_FACE_HUB_TOKEN
          valueFrom:
            secretKeyRef:
              name: hf-secret
              key: hf_api_token
        volumeMounts:
        - mountPath: /dev/shm
          name: dshm
      volumes:
      - name: dshm
        emptyDir:
            medium: Memory
      nodeSelector:
        cloud.google.com/gke-accelerator: nvidia-l4
        cloud.google.com/gke-gpu-driver-version: latest
---
apiVersion: v1
kind: Service
metadata:
  name: llm-service
spec:
  selector:
    app: gemma-server
  type: ClusterIP
  ports:
    - protocol: TCP
      port: 8000
      targetPort: 8000
# [END gke_ai_ml_llm_serving_gemma_vllm_3_12b_it_deployment]