ai-ml/llm-multiple-gpus/llama2-70b/text-generation-inference.yaml

# Copyright 2023 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_aiml_llm_multi_gpus_llama2_70b_inference]
apiVersion: apps/v1
kind: Deployment
metadata:
  name: llm
spec:
  replicas: 1
  selector:
    matchLabels:
      app: llm
  template:
    metadata:
      labels:
        app: llm
    spec:
      containers:
      - name: llm
        image: us-docker.pkg.dev/deeplearning-platform-release/gcr.io/huggingface-text-generation-inference-cu124.2-3.ubuntu2204.py311
        resources:
          requests:
            cpu: "10"
            memory: "60Gi"
            nvidia.com/gpu: "2"
          limits:
            cpu: "10"
            memory: "60Gi"
            nvidia.com/gpu: "2"
        env:
        - name: MODEL_ID
          value: meta-llama/Llama-2-70b-chat-hf
        - name: NUM_SHARD
          value: "2"
        - name: PORT
          value: "8080"
        - name: QUANTIZE
          value: bitsandbytes-nf4
        - name: HUGGING_FACE_HUB_TOKEN
          valueFrom:
            secretKeyRef:
              name: l4-demo
              key: HUGGING_FACE_TOKEN
        volumeMounts:
          - mountPath: /dev/shm
            name: dshm
          - mountPath: /data
            name: ephemeral-volume
      volumes:
        - name: dshm
          emptyDir:
              medium: Memory
        - name: ephemeral-volume
          ephemeral:
            volumeClaimTemplate:
              metadata:
                labels:
                  type: ephemeral
              spec:
                accessModes: ["ReadWriteOnce"]
                storageClassName: "premium-rwo"
                resources:
                  requests:
                    storage: 150Gi
      nodeSelector:
        cloud.google.com/gke-accelerator: "nvidia-l4"
        cloud.google.com/gke-spot: "true"
# [END gke_aiml_llm_multi_gpus_llama2_70b_inference]