GKE で複数の GPU を使用して LLM を提供する

コレクションでコンテンツを整理 必要に応じて、コンテンツの保存と分類を行います。

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-cu121.2-1.ubuntu2204.py310
        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/Meta-Llama-3-70B-Instruct
        - name: NUM_SHARD
          value: "2"
        - name: MAX_INPUT_TOKENS
          value: "2048"
        - 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 is set to /tmp as it's the path where the HUGGINGFACE_HUB_CACHE environment
          # variable in the TGI DLCs is set to instead of the default /data set within the TGI default image.
          # i.e. where the downloaded model from the Hub will be stored
          - mountPath: /tmp
            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"

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: "5"
            memory: "40Gi"
            nvidia.com/gpu: "2"
          limits:
            cpu: "5"
            memory: "40Gi"
            nvidia.com/gpu: "2"
        env:
        - name: MODEL_ID
          value: mistralai/Mixtral-8x7B-Instruct-v0.1
        - 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 is set to /tmp as it's the path where the HF_HOME environment
          # variable in the TGI DLCs is set to instead of the default /data set within the TGI default image.
          # i.e. where the downloaded model from the Hub will be stored
          - mountPath: /tmp
            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: 100Gi
      nodeSelector:
        cloud.google.com/gke-accelerator: "nvidia-l4"
        cloud.google.com/gke-spot: "true"

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-cu121.1-4.ubuntu2204.py310
        resources:
          requests:
            cpu: "10"
            memory: "60Gi"
            nvidia.com/gpu: "2"
          limits:
            cpu: "10"
            memory: "60Gi"
            nvidia.com/gpu: "2"
        env:
        - name: MODEL_ID
          value: tiiuae/falcon-40b-instruct
        - name: NUM_SHARD
          value: "2"
        - name: PORT
          value: "8080"
        - name: QUANTIZE
          value: bitsandbytes-nf4
        volumeMounts:
          - mountPath: /dev/shm
            name: dshm
          # mountPath is set to /data as it's the path where the HUGGINGFACE_HUB_CACHE environment
          # variable points to in the TGI container image i.e. where the downloaded model from the Hub will be
          # stored
          - 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: 175Gi
      nodeSelector:
        cloud.google.com/gke-accelerator: "nvidia-l4"
        cloud.google.com/gke-spot: "true"

apiVersion: apps/v1
kind: Deployment
metadata:
  name: gradio
  labels:
    app: gradio
spec:
  strategy:
    type: Recreate
  replicas: 1
  selector:
    matchLabels:
      app: gradio
  template:
    metadata:
      labels:
        app: gradio
    spec:
      containers:
      - name: gradio
        image: us-docker.pkg.dev/google-samples/containers/gke/gradio-app:v1.0.4
        resources:
          requests:
            cpu: "512m"
            memory: "512Mi"
          limits:
            cpu: "1"
            memory: "512Mi"
        env:
        - name: CONTEXT_PATH
          value: "/generate"
        - name: HOST
          value: "http://llm-service"
        - name: LLM_ENGINE
          value: "tgi"
        - name: MODEL_ID
          value: "meta-llama/Meta-Llama-3-70B-Instruct"
        - name: USER_PROMPT
          value: "<|begin_of_text|><|start_header_id|>user<|end_header_id|> prompt <|eot_id|><|start_header_id|>assistant<|end_header_id|>"
        - name: SYSTEM_PROMPT
          value: "prompt <|eot_id|>"
        ports:
        - containerPort: 7860
---
apiVersion: v1
kind: Service
metadata:
  name: gradio-service
spec:
  type: LoadBalancer
  selector:
    app: gradio
  ports:
  - port: 80
    targetPort: 7860

apiVersion: apps/v1
kind: Deployment
metadata:
  name: gradio
  labels:
    app: gradio
spec:
  strategy:
    type: Recreate
  replicas: 1
  selector:
    matchLabels:
      app: gradio
  template:
    metadata:
      labels:
        app: gradio
    spec:
      containers:
      - name: gradio
        image: us-docker.pkg.dev/google-samples/containers/gke/gradio-app:v1.0.4
        resources:
          requests:
            cpu: "512m"
            memory: "512Mi"
          limits:
            cpu: "1"
            memory: "512Mi"
        env:
        - name: CONTEXT_PATH
          value: "/generate"
        - name: HOST
          value: "http://llm-service"
        - name: LLM_ENGINE
          value: "tgi"
        - name: MODEL_ID
          value: "mixtral-8x7b"
        - name: USER_PROMPT
          value: "[INST] prompt [/INST]"
        - name: SYSTEM_PROMPT
          value: "prompt"
        ports:
        - containerPort: 7860
---
apiVersion: v1
kind: Service
metadata:
  name: gradio-service
spec:
  type: LoadBalancer
  selector:
    app: gradio
  ports:
  - port: 80
    targetPort: 7860

apiVersion: apps/v1
kind: Deployment
metadata:
  name: gradio
  labels:
    app: gradio
spec:
  strategy:
    type: Recreate
  replicas: 1
  selector:
    matchLabels:
      app: gradio
  template:
    metadata:
      labels:
        app: gradio
    spec:
      containers:
      - name: gradio
        image: us-docker.pkg.dev/google-samples/containers/gke/gradio-app:v1.0.4
        resources:
          requests:
            cpu: "512m"
            memory: "512Mi"
          limits:
            cpu: "1"
            memory: "512Mi"
        env:
        - name: CONTEXT_PATH
          value: "/generate"
        - name: HOST
          value: "http://llm-service"
        - name: LLM_ENGINE
          value: "tgi"
        - name: MODEL_ID
          value: "falcon-40b-instruct"
        - name: USER_PROMPT
          value: "User: prompt"
        - name: SYSTEM_PROMPT
          value: "Assistant: prompt"
        ports:
        - containerPort: 7860
---
apiVersion: v1
kind: Service
metadata:
  name: gradio-service
spec:
  type: LoadBalancer
  selector:
    app: gradio
  ports:
  - port: 80
    targetPort: 7860