ai-ml/llm-serving-optimum-tpu/optimum-tpu-gemma-2b-2x4.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_llm_serving_optimum_tpu_gemma_2b_2x4]
apiVersion: apps/v1
kind: Deployment
metadata:
  name: tgi-tpu
spec:
  replicas: 1
  selector:
    matchLabels:
      app: tgi-tpu
  template:
    metadata:
      labels:
        app: tgi-tpu
    spec:
      nodeSelector:
        cloud.google.com/gke-tpu-topology: 2x4
        cloud.google.com/gke-tpu-accelerator: tpu-v5-lite-podslice
      containers:
      - name: tgi-tpu
        image: REGION_NAME-docker.pkg.dev/PROJECT_ID/optimum-tpu/tgi-tpu:latest
        args:
        - --model-id=google/gemma-2b
        - --max-concurrent-requests=4
        - --max-input-length=8191
        - --max-total-tokens=8192
        - --max-batch-prefill-tokens=32768
        - --max-batch-size=16
        securityContext:
            privileged: true
        env:
          - name: HF_TOKEN
            valueFrom:
              secretKeyRef:
                name: hf-secret
                key: hf_api_token
        ports:
        - containerPort: 80
        resources:
          limits:
            google.com/tpu: 8
        livenessProbe:
          httpGet:
            path: /health
            port: 80
          initialDelaySeconds: 300
          periodSeconds: 120

---
apiVersion: v1
kind: Service
metadata:
  name: service
spec:
  selector:
    app: tgi-tpu
  ports:
    - name: http
      protocol: TCP
      port: 8080
      targetPort: 80

# [END gke_ai_ml_llm_serving_optimum_tpu_gemma_2b_2x4]