ai-ml/llm-serving-llama/vllm/vllm-llama4-maverick-17b-128e-instruct.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_vllm_llama_scout_17b_128e_instruct_deployment]
apiVersion: apps/v1
kind: Deployment
metadata:
  name: llama-deployment
spec:
  replicas: 1
  selector:
    matchLabels:
      app: llama-server
  template:
    metadata:
      labels:
        app: llama-server
        ai.gke.io/model: Llama-4-Maverick-17B-128E-Instruct
        ai.gke.io/inference-server: vllm
    spec:
      containers:
      - name: inference-server
        image: us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch-vllm-serve:20250405_1205_RC01
        resources:
          requests:
            cpu: 157
            memory: 2067Gi
            ephemeral-storage: 850Gi
            nvidia.com/gpu : 8
          limits:
            cpu: 157
            memory: 2067Gi
            ephemeral-storage: 850Gi
            nvidia.com/gpu : 8
        args:
        - python3
        - -m
        - vllm.entrypoints.api_server
        - --host=0.0.0.0
        - --port=7080
        - --swap-space=16
        - --max-model-len=131072
        - --gpu-memory-utilization=0.95
        - --disable-log-stats
        - --dtype=auto
        - --kv-cache-dtype=auto
        - --max-num-seqs=64
        - --model=meta-llama/Llama-4-Maverick-17B-128E-Instruct
        - --tensor-parallel-size=8
        env:
        - name: MODEL_ID
          value: 'meta-llama/Llama-4-Maverick-17B-128E-Instruct'
        - 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-h200-141gb
---
apiVersion: v1
kind: Service
metadata:
  name: llama-service
spec:
  selector:
    app: llama-server
  type: ClusterIP
  ports:
  - protocol: TCP
    port: 8000
    targetPort: 7080
---
apiVersion: v1
kind: Secret
metadata:
  name: hf-secret
type: Opaque
stringData:
  hf_api_token: {{HF_TOKEN}}
# [END gke_ai_ml_llm_serving_vllm_llama_scout_17b_128e_instruct_deployment]