k8s/llama3-70b.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.

apiVersion: apps/v1
kind: Deployment
metadata:
  name: vllm-openai-llama-deployment
spec:
  replicas: 1
  selector:
    matchLabels:
      app: openai-llama-server
  template:
    metadata:
      labels:
        app: openai-llama-server
    spec:
      containers:
      - name: inference-server
        image:  vllm/vllm-openai:v0.6.1
        resources:
          requests:
            cpu: "20"
            memory: "80Gi"
            ephemeral-storage: "100Gi"
            nvidia.com/gpu: "2"
          limits:
            cpu: "20"
            memory: "80Gi"
            ephemeral-storage: "100Gi"
            nvidia.com/gpu: "2"
        command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
        args:
        - --model=$(MODEL_ID)
        - --tensor-parallel-size=2
        - --max-model-len=128000
        - --kv-cache-dtype=fp8
        env:
        - name: MODEL_ID
          value: neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8
        - name: VLLM_WORKER_MULTIPROC_METHOD
          value: spawn
        - name: VLLM_ATTENTION_BACKEND
          value: FLASHINFER
        - 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-h100-80gb
        cloud.google.com/gke-gpu-driver-version: latest
---
apiVersion: v1
kind: Service
metadata:
  name: openai-llm-service
spec:
  selector:
    app: openai-llama-server
  type: ClusterIP
  ports:
    - protocol: TCP
      port: 8000
      targetPort: 8000