ai-ml/gke-ray/rayserve/llm/model-composition/ray-service.tpu-v5e-singlehost.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_gke_ray_rayserve_llm_model_composition_v5e_singlehost_tpu]
apiVersion: ray.io/v1
kind: RayService
metadata:
  name: vllm-tpu
spec:
  serveConfigV2: |
    applications:
    - name: llm
      route_prefix: /
      import_path:  ai-ml.gke-ray.rayserve.llm.model-composition.serve_tpu:multi_model
      deployments:
      - name: MultiModelDeployment
        num_replicas: 1
      runtime_env:
        working_dir: "https://github.com/GoogleCloudPlatform/kubernetes-engine-samples/archive/main.zip"
        env_vars:
          ASSIST_MODEL_ID: "$ASSIST_MODEL_ID"
          SUMMARIZER_MODEL_ID: "$SUMMARIZER_MODEL_ID"
          TPU_CHIPS: "16"
          TPU_HEADS: "2"
  rayClusterConfig:
    headGroupSpec:
      rayStartParams: {}
      template:
        metadata:
          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
          containers:
          - name: ray-head
            image: $VLLM_IMAGE
            resources:
              limits:
                cpu: "2"
                memory: 8G
              requests:
                cpu: "2"
                memory: 8G
            ports:
            - containerPort: 6379
              name: gcs-server
            - containerPort: 8265
              name: dashboard
            - containerPort: 10001
              name: client
            - containerPort: 8000
              name: serve
            env:
              - name: HUGGING_FACE_HUB_TOKEN
                valueFrom:
                  secretKeyRef:
                    name: hf-secret
                    key: hf_api_token
              - name: VLLM_XLA_CACHE_PATH
                value: "/data"
            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"
    workerGroupSpecs:
    - replicas: 2
      minReplicas: 1
      maxReplicas: 2
      numOfHosts: 1
      groupName: tpu-group
      rayStartParams: {}
      template:
        metadata:
          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
          containers:
          - name: llm
            image: $VLLM_IMAGE
            env:
              - name: HUGGING_FACE_HUB_TOKEN
                valueFrom:
                  secretKeyRef:
                    name: hf-secret
                    key: hf_api_token
              - name: VLLM_XLA_CACHE_PATH
                value: "/data"
            resources:
              limits:
                cpu: "100"
                google.com/tpu: "8"
                ephemeral-storage: 40G
                memory: 200G
              requests:
                cpu: "100"
                google.com/tpu: "8"
                ephemeral-storage: 40G
                memory: 200G
            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"
          nodeSelector:
            cloud.google.com/gke-tpu-accelerator: tpu-v5-lite-podslice
            cloud.google.com/gke-tpu-topology: 2x4
# [END gke_ai_ml_gke_ray_rayserve_llm_model_composition_v5e_singlehost_tpu]