Module lambda 

AWS Lambda Inference Deployment

Deploy and manage ML inference on AWS Lambda for serverless, pay-per-use inference.

Features

• Model packaging with Docker/OCI containers
• Cold start optimization with provisioned concurrency
• Automatic scaling with Lambda’s built-in capabilities
• Integration with Pacha registry for model artifacts

Toyota Way Principles

• Muda Elimination: Pay only for actual inference compute
• Heijunka: Automatic scaling levels inference load
• Jidoka: Built-in error handling and retry logic

Structs

DeploymentEstimate

Deployment estimate

InferenceRequest

Lambda inference request

InferenceResponse

Lambda inference response

LambdaClient

Lambda inference client

LambdaConfig

Lambda function configuration for inference

LambdaDeployer

Lambda deployment manager

VpcConfig

VPC configuration for Lambda

Enums

ConfigError

Configuration error

DeploymentError

Deployment error

DeploymentStatus

Deployment status

LambdaArchitecture

Lambda architecture

LambdaRuntime

Lambda runtime environment