ai-ml/vllm-tpu/vllm-llama3-70b.yaml

# Copyright 2024 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_vllm_tpu_vllm_llama3_70b]

apiVersion: apps/v1
kind: Deployment
metadata:
  name: vllm-tpu
spec:
  replicas: 1
  selector:
    matchLabels:
      app: vllm-tpu
  template:
    metadata:
      labels:
        app: vllm-tpu
      annotations:
        gke-gcsfuse/volumes: "true"
        gke-gcsfuse/cpu-limit: "0"
        gke-gcsfuse/memory-limit: "0"
        gke-gcsfuse/ephemeral-storage-limit: "0"
    spec:
      serviceAccountName: KSA_NAME
      nodeSelector:
        cloud.google.com/gke-tpu-topology: 2x4
        cloud.google.com/gke-tpu-accelerator: tpu-v6e-slice
      containers:
      - name: vllm-tpu
        image: docker.io/vllm/vllm-tpu:73aa7041bfee43581314e6f34e9a657137ecc092
        command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
        args:
        - --host=0.0.0.0
        - --port=8000
        - --tensor-parallel-size=8
        - --max-model-len=4096
        - --model=meta-llama/Llama-3.1-70B
        - --download-dir=/data
        - --max-num-batched-tokens=512
        - --max-num-seqs=128
        env: 
        - name: HUGGING_FACE_HUB_TOKEN
          valueFrom:
            secretKeyRef:
              name: hf-secret
              key: hf_api_token
        - name: VLLM_XLA_CACHE_PATH
          value: "/data"
        - name: VLLM_USE_V1
          value: "1"
        ports:
        - containerPort: 8000
        resources:
          limits:
            google.com/tpu: 8
        readinessProbe:
          tcpSocket:
            port: 8000
          initialDelaySeconds: 15
          periodSeconds: 10
        volumeMounts:
        - name: gcs-fuse-csi-ephemeral
          mountPath: /data
        - name: dshm
          mountPath: /dev/shm
      volumes:
      - name: gke-gcsfuse-cache
        emptyDir:
          medium: Memory
      - name: dshm
        emptyDir:
          medium: Memory
      - name: gcs-fuse-csi-ephemeral
        csi:
          driver: gcsfuse.csi.storage.gke.io
          volumeAttributes:
            bucketName: GSBUCKET
            mountOptions: "implicit-dirs,file-cache:enable-parallel-downloads:true,file-cache:parallel-downloads-per-file:100,file-cache:max-parallel-downloads:-1,file-cache:download-chunk-size-mb:10,file-cache:max-size-mb:-1"
---
apiVersion: v1
kind: Service
metadata:
  name: vllm-service
spec:
  selector:
    app: vllm-tpu
  type: LoadBalancer	
  ports:
    - name: http
      protocol: TCP
      port: 8000  
      targetPort: 8000

# [END gke_ai_ml_vllm_tpu_vllm_llama3_70b]