@pulumiverse/scaleway
Version:
A Pulumi package for creating and managing Scaleway cloud resources.
242 lines (241 loc) • 8.34 kB
TypeScript
import * as pulumi from "@pulumi/pulumi";
import * as inputs from "./types/input";
import * as outputs from "./types/output";
/**
* Creates and manages Scaleway Managed Inference deployments.
* For more information, see the [API documentation](https://www.scaleway.com/en/developers/api/inference/).
*
* ## Example Usage
*
* ## Import
*
* Functions can be imported using, `{region}/{id}`, as shown below:
*
* bash
*
* ```sh
* $ pulumi import scaleway:index/inferenceDeployment:InferenceDeployment deployment fr-par/11111111-1111-1111-1111-111111111111
* ```
*
* @deprecated scaleway.index/inferencedeployment.InferenceDeployment has been deprecated in favor of scaleway.inference/deployment.Deployment
*/
export declare class InferenceDeployment extends pulumi.CustomResource {
/**
* Get an existing InferenceDeployment resource's state with the given name, ID, and optional extra
* properties used to qualify the lookup.
*
* @param name The _unique_ name of the resulting resource.
* @param id The _unique_ provider ID of the resource to lookup.
* @param state Any extra arguments used during the lookup.
* @param opts Optional settings to control the behavior of the CustomResource.
*/
static get(name: string, id: pulumi.Input<pulumi.ID>, state?: InferenceDeploymentState, opts?: pulumi.CustomResourceOptions): InferenceDeployment;
/**
* Returns true if the given object is an instance of InferenceDeployment. This is designed to work even
* when multiple copies of the Pulumi SDK have been loaded into the same process.
*/
static isInstance(obj: any): obj is InferenceDeployment;
/**
* Some models (e.g Meta Llama) require end-user license agreements. Set `true` to accept.
*/
readonly acceptEula: pulumi.Output<boolean | undefined>;
/**
* The date and time of the creation of the deployment.
*/
readonly createdAt: pulumi.Output<string>;
/**
* The maximum size of the pool.
*/
readonly maxSize: pulumi.Output<number | undefined>;
/**
* The minimum size of the pool.
*/
readonly minSize: pulumi.Output<number | undefined>;
/**
* The model id used for the deployment.
*/
readonly modelId: pulumi.Output<string>;
/**
* The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (`scw inference model list`)
*/
readonly modelName: pulumi.Output<string>;
/**
* The deployment name.
*/
readonly name: pulumi.Output<string>;
/**
* The node type to use for the deployment. Node types can be found using Scaleway's CLI (`scw inference node-type list`)
*/
readonly nodeType: pulumi.Output<string>;
/**
* Configuration of the deployment's private endpoint.
*/
readonly privateEndpoint: pulumi.Output<outputs.InferenceDeploymentPrivateEndpoint | undefined>;
/**
* `projectId`) The ID of the project the deployment is associated with.
*/
readonly projectId: pulumi.Output<string>;
/**
* Configuration of the deployment's public endpoint.
*/
readonly publicEndpoint: pulumi.Output<outputs.InferenceDeploymentPublicEndpoint | undefined>;
/**
* The number of bits each model parameter should be quantized to
*/
readonly quantization: pulumi.Output<number | undefined>;
/**
* `region`) The region in which the deployment is created.
*/
readonly region: pulumi.Output<string>;
/**
* The size of the pool.
*/
readonly size: pulumi.Output<number>;
/**
* The status of the deployment.
*/
readonly status: pulumi.Output<string>;
/**
* The tags associated with the deployment.
*/
readonly tags: pulumi.Output<string[] | undefined>;
/**
* The date and time of the last update of the deployment.
*/
readonly updatedAt: pulumi.Output<string>;
/**
* Create a InferenceDeployment resource with the given unique name, arguments, and options.
*
* @param name The _unique_ name of the resource.
* @param args The arguments to use to populate this resource's properties.
* @param opts A bag of options that control this resource's behavior.
*/
/** @deprecated scaleway.index/inferencedeployment.InferenceDeployment has been deprecated in favor of scaleway.inference/deployment.Deployment */
constructor(name: string, args: InferenceDeploymentArgs, opts?: pulumi.CustomResourceOptions);
}
/**
* Input properties used for looking up and filtering InferenceDeployment resources.
*/
export interface InferenceDeploymentState {
/**
* Some models (e.g Meta Llama) require end-user license agreements. Set `true` to accept.
*/
acceptEula?: pulumi.Input<boolean>;
/**
* The date and time of the creation of the deployment.
*/
createdAt?: pulumi.Input<string>;
/**
* The maximum size of the pool.
*/
maxSize?: pulumi.Input<number>;
/**
* The minimum size of the pool.
*/
minSize?: pulumi.Input<number>;
/**
* The model id used for the deployment.
*/
modelId?: pulumi.Input<string>;
/**
* The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (`scw inference model list`)
*/
modelName?: pulumi.Input<string>;
/**
* The deployment name.
*/
name?: pulumi.Input<string>;
/**
* The node type to use for the deployment. Node types can be found using Scaleway's CLI (`scw inference node-type list`)
*/
nodeType?: pulumi.Input<string>;
/**
* Configuration of the deployment's private endpoint.
*/
privateEndpoint?: pulumi.Input<inputs.InferenceDeploymentPrivateEndpoint>;
/**
* `projectId`) The ID of the project the deployment is associated with.
*/
projectId?: pulumi.Input<string>;
/**
* Configuration of the deployment's public endpoint.
*/
publicEndpoint?: pulumi.Input<inputs.InferenceDeploymentPublicEndpoint>;
/**
* The number of bits each model parameter should be quantized to
*/
quantization?: pulumi.Input<number>;
/**
* `region`) The region in which the deployment is created.
*/
region?: pulumi.Input<string>;
/**
* The size of the pool.
*/
size?: pulumi.Input<number>;
/**
* The status of the deployment.
*/
status?: pulumi.Input<string>;
/**
* The tags associated with the deployment.
*/
tags?: pulumi.Input<pulumi.Input<string>[]>;
/**
* The date and time of the last update of the deployment.
*/
updatedAt?: pulumi.Input<string>;
}
/**
* The set of arguments for constructing a InferenceDeployment resource.
*/
export interface InferenceDeploymentArgs {
/**
* Some models (e.g Meta Llama) require end-user license agreements. Set `true` to accept.
*/
acceptEula?: pulumi.Input<boolean>;
/**
* The maximum size of the pool.
*/
maxSize?: pulumi.Input<number>;
/**
* The minimum size of the pool.
*/
minSize?: pulumi.Input<number>;
/**
* The model id used for the deployment.
*/
modelId: pulumi.Input<string>;
/**
* The deployment name.
*/
name?: pulumi.Input<string>;
/**
* The node type to use for the deployment. Node types can be found using Scaleway's CLI (`scw inference node-type list`)
*/
nodeType: pulumi.Input<string>;
/**
* Configuration of the deployment's private endpoint.
*/
privateEndpoint?: pulumi.Input<inputs.InferenceDeploymentPrivateEndpoint>;
/**
* `projectId`) The ID of the project the deployment is associated with.
*/
projectId?: pulumi.Input<string>;
/**
* Configuration of the deployment's public endpoint.
*/
publicEndpoint?: pulumi.Input<inputs.InferenceDeploymentPublicEndpoint>;
/**
* The number of bits each model parameter should be quantized to
*/
quantization?: pulumi.Input<number>;
/**
* `region`) The region in which the deployment is created.
*/
region?: pulumi.Input<string>;
/**
* The tags associated with the deployment.
*/
tags?: pulumi.Input<pulumi.Input<string>[]>;
}