ai-ml/llm-multihost-gpus/vllm-llama3-405b-A3.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_multihost_gpus_vllm_llama3_405b_a4]

apiVersion: leaderworkerset.x-k8s.io/v1
kind: LeaderWorkerSet
metadata:
  name: vllm
spec:
  replicas: 1
  leaderWorkerTemplate:
    size: 2
    restartPolicy: RecreateGroupOnPodRestart
    leaderTemplate:
      metadata:
        labels:
          role: leader
      spec:
        nodeSelector:
          cloud.google.com/gke-accelerator: nvidia-h100-80gb
        containers:
          - name: vllm-leader
            image: docker.io/vllm/vllm-openai:latest
            env:
              - name: HUGGING_FACE_HUB_TOKEN
                valueFrom:
                  secretKeyRef:
                    name: hf-secret
                    key: hf_api_token
            command:
              - sh
              - -c
              - "bash /vllm-workspace/examples/online_serving/multi-node-serving.sh leader --ray_cluster_size=$(LWS_GROUP_SIZE);
                python3 -m vllm.entrypoints.openai.api_server --port 8080 --model meta-llama/Meta-Llama-3.1-405B-Instruct --tensor-parallel-size 8 --pipeline-parallel-size 2"
            resources:
              limits:
                nvidia.com/gpu: "8"
            ports:
              - containerPort: 8080
            readinessProbe:
              tcpSocket:
                port: 8080
              initialDelaySeconds: 15
              periodSeconds: 10
            volumeMounts:
              - mountPath: /dev/shm
                name: dshm
        volumes:
        - name: dshm
          emptyDir:
            medium: Memory
            sizeLimit: 15Gi
    workerTemplate:
      spec:
        nodeSelector:
          cloud.google.com/gke-accelerator: nvidia-h100-80gb
        containers:
          - name: vllm-worker
            image: docker.io/vllm/vllm-openai:latest
            command:
              - sh
              - -c
              - "bash /vllm-workspace/examples/online_serving/multi-node-serving.sh worker --ray_address=$(LWS_LEADER_ADDRESS)"
            resources:
              limits:
                nvidia.com/gpu: "8"
            env:
              - 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
            sizeLimit: 15Gi
---
apiVersion: v1
kind: Service
metadata:
  name: vllm-leader
spec:
  ports:
    - name: http
      port: 8080
      protocol: TCP
      targetPort: 8080
  selector:
    leaderworkerset.sigs.k8s.io/name: vllm
    role: leader
  type: ClusterIP

  # [END gke_ai_ml_llm_serving_multihost_gpus_vllm_llama3_405b_a4]