aws-cdk-neuronx-patterns/lib/base/neuronx-compiler/neuronx-compiler.d.ts

> [!WARNING] > This library is experimental module.

import { Size } from "aws-cdk-lib";
import * as batch from "aws-cdk-lib/aws-batch";
import * as ec2 from "aws-cdk-lib/aws-ec2";
import { ContainerImage } from "aws-cdk-lib/aws-ecs";
import { IBucket } from "aws-cdk-lib/aws-s3";
import { Construct } from "constructs";
import { INeuronxInstanceType, Model } from "../neuronx";
/**
 * Compile runtime.
 */
export interface INeuronxContainerImage {
    /**
     * An image of the container where the compile job is executed.
     */
    readonly image: ContainerImage;
    /**
     * Neuronx version included in container image.
     */
    readonly sdkVersion: string;
}
/**
 * Props of NeuronxCompiler.
 */
export interface NeuronxCompilerProps {
    /**
     * VPC in which this will launch compile worker instance.
     */
    readonly vpc: ec2.IVpc;
    /**
     * The bucket to upload compiled artifacts.
     */
    readonly bucket: IBucket;
    /**
     * Secrets to pass to the container.
     */
    readonly secrets?: {
        [key: string]: batch.Secret;
    };
    /**
     * S3 Prefix that compiled artifact uploaded.
     * This property is not depends on compile job finish.
     */
    readonly artifactS3Prefix: string;
    /**
     * The instance type of compile worker instance.
     */
    readonly neuronxInstanceType: INeuronxInstanceType;
    /**
     * The model to be compiled.
     */
    readonly model: Model;
    /**
     * An image of the container where the compile job is executed.
     */
    readonly image: INeuronxContainerImage;
    readonly command?: string[];
    /**
     * The root volume of worker instance.
     * @default - N bilion parameters * 5GiB EBS
     */
    readonly volumeSize?: Size;
    /**
     * Whether or not to use spot instances. Spot instances are less expensive EC2 instances that can be reclaimed by EC2 at any time; your job will be given two minutes of notice before reclamation.
     *
     * @default false
     */
    readonly spot?: boolean;
    /**
     * The VPC Subnets this Compute Environment will launch instances in.
     *
     * @default - new subnets will be created
     */
    readonly vpcSubnets?: ec2.SubnetSelection;
    /**
     * The environment variables to pass to the container.
     * This is only applicable when using container runtime.
     *
     * @default - No environment variables.
     */
    readonly environment?: {
        [key: string]: string;
    };
}
export interface NeuronxCompiledModel {
    readonly compileTimeInstanceType: INeuronxInstanceType;
    /**
     * The bucket to upload compiled artifacts.
     */
    readonly bucket: IBucket;
    /**
     * S3 URL that compiled artifact uploaded.
     */
    readonly s3Uri: string;
    /**
     * S3 prefix that compiled artifact uploaded.
     */
    readonly s3Prefix: string;
    /**
     * The model name.
     */
    readonly modelName: string;
    readonly weightSize: Size;
}
/**
 * Neuronx compiler construct.
 * Compile the model to work with Inferentia2 and Trainium1 and upload it to an S3 bucket.
 */
export declare class NeuronxCompiler extends Construct {
    private compiledModel?;
    private readonly entrypoint;
    private readonly jobDefinition;
    private readonly jobQueue;
    private readonly artifactS3Prefix;
    private readonly weightSize;
    private readonly neuronxInstanceType;
    private readonly model;
    private readonly bucket;
    constructor(scope: Construct, id: string, props: NeuronxCompilerProps);
    compile(): NeuronxCompiledModel;
}