ai-ml/llm-serving-gemma/tgi/tgi-2-9b.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_gemma_tgi_2_9b_deployment]
apiVersion: apps/v1
kind: Deployment
metadata:
  name: tgi-gemma-deployment
spec:
  replicas: 1
  selector:
    matchLabels:
      app: gemma-server
  template:
    metadata:
      labels:
        app: gemma-server
        ai.gke.io/model: gemma-2-9b
        ai.gke.io/inference-server: text-generation-inference
        examples.ai.gke.io/source: user-guide
    spec:
      containers:
      - name: inference-server
        image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311
        resources:
          requests:
            cpu: "4"
            memory: "30Gi"
            ephemeral-storage: "30Gi"
            nvidia.com/gpu: "2"
          limits:
            cpu: "4"
            memory: "30Gi"
            ephemeral-storage: "30Gi"
            nvidia.com/gpu: "2"
        env:
        - name: AIP_HTTP_PORT
          value: '8000'
        - name: NUM_SHARD
          value: '2'
        - name: MAX_INPUT_LENGTH
          value: '1562'
        - name: MAX_TOTAL_TOKENS
          value: '2048'
        - name: MAX_BATCH_PREFILL_TOKENS
          value: '2048'
        - name: CUDA_MEMORY_FRACTION
          value: '0.93'
        - name: MODEL_ID
          value: google/gemma-2-9b
        - 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
---
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_tgi_2_9b_deployment]