Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

apiVersion: batch/v1
kind: Job
metadata:
  name: mig-job
  namespace: default
spec:
  template:
    spec:
      containers:
      - name: pytorch
        image: pytorch/pytorch:latest
        resources:
          requests:
            nvidia.com/mig-1g.5gb: 1
            cpu: "100m"
            memory: "128Mi"
          limits:
            nvidia.com/mig-1g.5gb: 1
      restartPolicy: Never

# Deploy JumpStart model with MIG
hyp create hyp-jumpstart-endpoint \
  --model-id deepseek-llm-r1-distill-qwen-1-5b \
  --instance-type ml.p5.48xlarge \
  --accelerator-partition-type mig-2g.10gb \
  --accelerator-partition-validation True \
  --endpoint-name my-endpoint \
  --tls-certificate-output-s3-uri s3://certificate-bucket/ \
  --namespace default

apiVersion: inference.sagemaker.aws.amazon.com/v1
kind: JumpStartModel
metadata:
  name: deepseek-model
  namespace: default
spec:
  sageMakerEndpoint:
    name: deepseek-endpoint
  model:
    modelHubName: SageMakerPublicHub
    modelId: deepseek-llm-r1-distill-qwen-1-5b
  server:
    acceleratorPartitionType: mig-7g.40gb
    instanceType: ml.p4d.24xlarge

apiVersion: inference.sagemaker.aws.amazon.com/v1
kind: InferenceEndpointConfig
metadata:
  name: custom-model
  namespace: default
spec:
  replicas: 1
  modelName: my-model
  endpointName: my-endpoint
  instanceType: ml.p4d.24xlarge
  modelSourceConfig:
    modelSourceType: s3
    s3Storage:
      bucketName: my-model-bucket
      region: us-east-2
    modelLocation: model-path
  worker:
    resources:
      requests:
        nvidia.com/mig-3g.20gb: 1
        cpu: "5600m"
        memory: "10Gi"
      limits:
        nvidia.com/mig-3g.20gb: 1

apiVersion: inference.sagemaker.aws.amazon.com/v1
kind: InferenceEndpointConfig
metadata:
  name: custom-model
  namespace: default
spec:
  replicas: 1
  modelName: my-model
  endpointName: my-endpoint
  instanceType: ml.p4d.24xlarge
  modelSourceConfig:
    modelSourceType: fsx
    fsxStorage:
      fileSystemId: fs-xxxxx
    modelLocation: location-on-fsx
  worker:
    resources:
      requests:
        nvidia.com/mig-3g.20gb: 1
        cpu: "5600m"
        memory: "10Gi"
      limits:
        nvidia.com/mig-3g.20gb: 1

hyp create hyp-jumpstart-endpoint \
  --version 1.1 \
  --model-id deepseek-llm-r1-distill-qwen-1-5b \
  --instance-type ml.p4d.24xlarge \
  --endpoint-name js-test \
  --accelerator-partition-type "mig-4g.20gb" \
  --accelerator-partition-validation true \
  --tls-certificate-output-s3-uri s3://my-bucket/certs/

hyp create hyp-custom-endpoint \
  --namespace default \
  --metadata-name deepseek15b-mig-10-14-v2 \
  --endpoint-name deepseek15b-mig-endpoint \
  --instance-type ml.p4d.24xlarge \
  --model-name deepseek15b-mig \
  --model-source-type s3 \
  --model-location deep-seek-15b \
  --prefetch-enabled true \
  --tls-certificate-output-s3-uri s3://sagemaker-bucket \
  --image-uri lmcache/vllm-openai:v0.3.7 \
  --container-port 8080 \
  --model-volume-mount-path /opt/ml/model \
  --model-volume-mount-name model-weights \
  --s3-bucket-name model-storage-123456789 \
  --s3-region us-east-2 \
  --invocation-endpoint invocations \
  --resources-requests '{"cpu":"5600m","memory":"10Gi","nvidia.com/mig-3g.20gb":"1"}' \
  --resources-limits '{"nvidia.com/mig-3g.20gb":"1"}' \
  --env '{
    "OPTION_ROLLING_BATCH":"vllm",
    "SERVING_CHUNKED_READ_TIMEOUT":"480",
    "DJL_OFFLINE":"true",
    "NUM_SHARD":"1",
    "SAGEMAKER_PROGRAM":"inference.py",
    "SAGEMAKER_SUBMIT_DIRECTORY":"/opt/ml/model/code",
    "MODEL_CACHE_ROOT":"/opt/ml/model",
    "SAGEMAKER_MODEL_SERVER_WORKERS":"1",
    "SAGEMAKER_MODEL_SERVER_TIMEOUT":"3600",
    "OPTION_TRUST_REMOTE_CODE":"true",
    "OPTION_ENABLE_REASONING":"true",
    "OPTION_REASONING_PARSER":"deepseek_r1",
    "SAGEMAKER_CONTAINER_LOG_LEVEL":"20",
    "SAGEMAKER_ENV":"1"
  }'