Amazon SageMaker が基盤モデルのデプロイコストとレイテンシーの低減に役立つ新しい推論機能を追加

import boto3
import sagemaker

role = sagemaker.get_execution_role()
sm_client = boto3.client(service_name="sagemaker")

sm_client.create_endpoint_config(
    EndpointConfigName=endpoint_config_name,
    ExecutionRoleArn=role,
    ProductionVariants=[{
        "VariantName": "AllTraffic",
        "InstanceType": "ml.g5.12xlarge",
        "InitialInstanceCount": 1,
		"RoutingConfig": {
            "RoutingStrategy": "LEAST_OUTSTANDING_REQUESTS"
        }
    }]
)

sm_client.create_endpoint(
    EndpointName=endpoint_name,
    EndpointConfigName=endpoint_config_name,
)

from sagemaker.huggingface import get_huggingface_llm_image_uri

# コンテナイメージの URI を取得します
hf_inference_dlc = get_huggingface_llm_image_uri(
  "huggingface",
  version="0.9.3"
)

# モデルコンテナを設定します
dolly7b = {
    'Image': hf_inference_dlc,
    'Environment': {
        'HF_MODEL_ID':'databricks/dolly-v2-7b',
        'HF_TASK':'text-generation',
    }
}

# SageMaker モデルを作成します
sagemaker_client.create_model(
    ModelName        = "dolly-v2-7b",
    ExecutionRoleArn = role,
    Containers       = [dolly7b]
)

# モデルコンテナを設定します
flant5xxlmodel = {
    'Image': hf_inference_dlc,
    'Environment': {
        'HF_MODEL_ID':'google/flan-t5-xxl',
        'HF_TASK':'text-generation',
    }
}

# SageMaker モデルを作成します
sagemaker_client.create_model(
    ModelName        = "flan-t5-xxl",
    ExecutionRoleArn = role,
    Containers       = [flant5xxlmodel]
)

# Dolly v2 7B の推論コンポーネント
sm_client.create_inference_component(
    InferenceComponentName="IC-dolly-v2-7b",
    EndpointName=endpoint_name,
    VariantName=variant_name,
    Specification={
        "ModelName": "dolly-v2-7b",
        "ComputeResourceRequirements": {
		    "NumberOfAcceleratorDevicesRequired": 2,
			"NumberOfCpuCoresRequired": 2,
			"MinMemoryRequiredInMb": 1024
	    }
    },
    RuntimeConfig={"CopyCount": 1},
)

# FLAN-T5 XXL の推論コンポーネント
sm_client.create_inference_component(
    InferenceComponentName="IC-flan-t5-xxl",
    EndpointName=endpoint_name,
    VariantName=variant_name,
    Specification={
        "ModelName": "flan-t5-xxl",
        "ComputeResourceRequirements": {
		    "NumberOfAcceleratorDevicesRequired": 2,
			"NumberOfCpuCoresRequired": 1,
			"MinMemoryRequiredInMb": 1024
	    }
    },
    RuntimeConfig={"CopyCount": 1},
)

import json
sm_runtime_client = boto3.client(service_name="sagemaker-runtime")
payload = {"inputs": "Why is California a great place to live?"}

response_dolly = sm_runtime_client.invoke_endpoint(
    EndpointName=endpoint_name,
    InferenceComponentName = "IC-dolly-v2-7b",
    ContentType="application/json",
    Accept="application/json",
    Body=json.dumps(payload),
)

response_flant5 = sm_runtime_client.invoke_endpoint(
    EndpointName=endpoint_name,
    InferenceComponentName = "IC-flan-t5-xxl",
    ContentType="application/json",
    Accept="application/json",
    Body=json.dumps(payload),
)

result_dolly = json.loads(response_dolly['Body'].read().decode())
result_flant5 = json.loads(response_flant5['Body'].read().decode())