scaleway.inference.Deployment
Creates and manages Scaleway Managed Inference deployments. For more information, see the API documentation.
Example Usage
Basic
Example coming soon!
Example coming soon!
Example coming soon!
Example coming soon!
Example coming soon!
resources:
  deployment:
    type: scaleway:inference:Deployment
    properties:
      name: tf-inference-deployment
      nodeType: L4
      modelName: ${myModel.id}
      publicEndpoint:
        isEnabled: true
      acceptEula: true
variables:
  myModel:
    fn::invoke:
      function: scaleway:inference:getModel
      arguments:
        name: meta/llama-3.1-8b-instruct:fp8
Create Deployment Resource
Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.
Constructor syntax
new Deployment(name: string, args: DeploymentArgs, opts?: CustomResourceOptions);@overload
def Deployment(resource_name: str,
               args: DeploymentArgs,
               opts: Optional[ResourceOptions] = None)
@overload
def Deployment(resource_name: str,
               opts: Optional[ResourceOptions] = None,
               model_id: Optional[str] = None,
               node_type: Optional[str] = None,
               private_endpoint: Optional[DeploymentPrivateEndpointArgs] = None,
               min_size: Optional[int] = None,
               name: Optional[str] = None,
               max_size: Optional[int] = None,
               accept_eula: Optional[bool] = None,
               private_ips: Optional[Sequence[DeploymentPrivateIpArgs]] = None,
               project_id: Optional[str] = None,
               public_endpoint: Optional[DeploymentPublicEndpointArgs] = None,
               quantization: Optional[int] = None,
               region: Optional[str] = None,
               tags: Optional[Sequence[str]] = None)func NewDeployment(ctx *Context, name string, args DeploymentArgs, opts ...ResourceOption) (*Deployment, error)public Deployment(string name, DeploymentArgs args, CustomResourceOptions? opts = null)
public Deployment(String name, DeploymentArgs args)
public Deployment(String name, DeploymentArgs args, CustomResourceOptions options)
type: scaleway:inference:Deployment
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.
Parameters
- name string
- The unique name of the resource.
- args DeploymentArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- resource_name str
- The unique name of the resource.
- args DeploymentArgs
- The arguments to resource properties.
- opts ResourceOptions
- Bag of options to control resource's behavior.
- ctx Context
- Context object for the current deployment.
- name string
- The unique name of the resource.
- args DeploymentArgs
- The arguments to resource properties.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args DeploymentArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resource.
- args DeploymentArgs
- The arguments to resource properties.
- options CustomResourceOptions
- Bag of options to control resource's behavior.
Constructor example
The following reference example uses placeholder values for all input properties.
var deploymentResource = new Scaleway.Inference.Deployment("deploymentResource", new()
{
    ModelId = "string",
    NodeType = "string",
    PrivateEndpoint = new Scaleway.Inference.Inputs.DeploymentPrivateEndpointArgs
    {
        DisableAuth = false,
        Id = "string",
        PrivateNetworkId = "string",
        Url = "string",
    },
    MinSize = 0,
    Name = "string",
    MaxSize = 0,
    AcceptEula = false,
    PrivateIps = new[]
    {
        new Scaleway.Inference.Inputs.DeploymentPrivateIpArgs
        {
            Address = "string",
            Id = "string",
        },
    },
    ProjectId = "string",
    PublicEndpoint = new Scaleway.Inference.Inputs.DeploymentPublicEndpointArgs
    {
        DisableAuth = false,
        Id = "string",
        IsEnabled = false,
        Url = "string",
    },
    Quantization = 0,
    Region = "string",
    Tags = new[]
    {
        "string",
    },
});
example, err := inference.NewDeployment(ctx, "deploymentResource", &inference.DeploymentArgs{
	ModelId:  pulumi.String("string"),
	NodeType: pulumi.String("string"),
	PrivateEndpoint: &inference.DeploymentPrivateEndpointArgs{
		DisableAuth:      pulumi.Bool(false),
		Id:               pulumi.String("string"),
		PrivateNetworkId: pulumi.String("string"),
		Url:              pulumi.String("string"),
	},
	MinSize:    pulumi.Int(0),
	Name:       pulumi.String("string"),
	MaxSize:    pulumi.Int(0),
	AcceptEula: pulumi.Bool(false),
	PrivateIps: inference.DeploymentPrivateIpArray{
		&inference.DeploymentPrivateIpArgs{
			Address: pulumi.String("string"),
			Id:      pulumi.String("string"),
		},
	},
	ProjectId: pulumi.String("string"),
	PublicEndpoint: &inference.DeploymentPublicEndpointArgs{
		DisableAuth: pulumi.Bool(false),
		Id:          pulumi.String("string"),
		IsEnabled:   pulumi.Bool(false),
		Url:         pulumi.String("string"),
	},
	Quantization: pulumi.Int(0),
	Region:       pulumi.String("string"),
	Tags: pulumi.StringArray{
		pulumi.String("string"),
	},
})
var deploymentResource = new Deployment("deploymentResource", DeploymentArgs.builder()
    .modelId("string")
    .nodeType("string")
    .privateEndpoint(DeploymentPrivateEndpointArgs.builder()
        .disableAuth(false)
        .id("string")
        .privateNetworkId("string")
        .url("string")
        .build())
    .minSize(0)
    .name("string")
    .maxSize(0)
    .acceptEula(false)
    .privateIps(DeploymentPrivateIpArgs.builder()
        .address("string")
        .id("string")
        .build())
    .projectId("string")
    .publicEndpoint(DeploymentPublicEndpointArgs.builder()
        .disableAuth(false)
        .id("string")
        .isEnabled(false)
        .url("string")
        .build())
    .quantization(0)
    .region("string")
    .tags("string")
    .build());
deployment_resource = scaleway.inference.Deployment("deploymentResource",
    model_id="string",
    node_type="string",
    private_endpoint={
        "disable_auth": False,
        "id": "string",
        "private_network_id": "string",
        "url": "string",
    },
    min_size=0,
    name="string",
    max_size=0,
    accept_eula=False,
    private_ips=[{
        "address": "string",
        "id": "string",
    }],
    project_id="string",
    public_endpoint={
        "disable_auth": False,
        "id": "string",
        "is_enabled": False,
        "url": "string",
    },
    quantization=0,
    region="string",
    tags=["string"])
const deploymentResource = new scaleway.inference.Deployment("deploymentResource", {
    modelId: "string",
    nodeType: "string",
    privateEndpoint: {
        disableAuth: false,
        id: "string",
        privateNetworkId: "string",
        url: "string",
    },
    minSize: 0,
    name: "string",
    maxSize: 0,
    acceptEula: false,
    privateIps: [{
        address: "string",
        id: "string",
    }],
    projectId: "string",
    publicEndpoint: {
        disableAuth: false,
        id: "string",
        isEnabled: false,
        url: "string",
    },
    quantization: 0,
    region: "string",
    tags: ["string"],
});
type: scaleway:inference:Deployment
properties:
    acceptEula: false
    maxSize: 0
    minSize: 0
    modelId: string
    name: string
    nodeType: string
    privateEndpoint:
        disableAuth: false
        id: string
        privateNetworkId: string
        url: string
    privateIps:
        - address: string
          id: string
    projectId: string
    publicEndpoint:
        disableAuth: false
        id: string
        isEnabled: false
        url: string
    quantization: 0
    region: string
    tags:
        - string
Deployment Resource Properties
To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.
Inputs
In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.
The Deployment resource accepts the following input properties:
- ModelId string
- The model id used for the deployment.
- NodeType string
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- AcceptEula bool
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- MaxSize int
- The maximum size of the pool.
- MinSize int
- The minimum size of the pool.
- Name string
- The deployment name.
- PrivateEndpoint Pulumiverse.Scaleway. Inference. Inputs. Deployment Private Endpoint 
- Configuration of the deployment's private endpoint.
- PrivateIps List<Pulumiverse.Scaleway. Inference. Inputs. Deployment Private Ip> 
- The private IPv4 address associated with the deployment.
- ProjectId string
- project_id) The ID of the project the deployment is associated with.
- PublicEndpoint Pulumiverse.Scaleway. Inference. Inputs. Deployment Public Endpoint 
- Configuration of the deployment's public endpoint.
- Quantization int
- The number of bits each model parameter should be quantized to
- Region string
- region) The region in which the deployment is created.
- List<string>
- The tags associated with the deployment.
- ModelId string
- The model id used for the deployment.
- NodeType string
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- AcceptEula bool
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- MaxSize int
- The maximum size of the pool.
- MinSize int
- The minimum size of the pool.
- Name string
- The deployment name.
- PrivateEndpoint DeploymentPrivate Endpoint Args 
- Configuration of the deployment's private endpoint.
- PrivateIps []DeploymentPrivate Ip Args 
- The private IPv4 address associated with the deployment.
- ProjectId string
- project_id) The ID of the project the deployment is associated with.
- PublicEndpoint DeploymentPublic Endpoint Args 
- Configuration of the deployment's public endpoint.
- Quantization int
- The number of bits each model parameter should be quantized to
- Region string
- region) The region in which the deployment is created.
- []string
- The tags associated with the deployment.
- modelId String
- The model id used for the deployment.
- nodeType String
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- acceptEula Boolean
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- maxSize Integer
- The maximum size of the pool.
- minSize Integer
- The minimum size of the pool.
- name String
- The deployment name.
- privateEndpoint DeploymentPrivate Endpoint 
- Configuration of the deployment's private endpoint.
- privateIps List<DeploymentPrivate Ip> 
- The private IPv4 address associated with the deployment.
- projectId String
- project_id) The ID of the project the deployment is associated with.
- publicEndpoint DeploymentPublic Endpoint 
- Configuration of the deployment's public endpoint.
- quantization Integer
- The number of bits each model parameter should be quantized to
- region String
- region) The region in which the deployment is created.
- List<String>
- The tags associated with the deployment.
- modelId string
- The model id used for the deployment.
- nodeType string
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- acceptEula boolean
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- maxSize number
- The maximum size of the pool.
- minSize number
- The minimum size of the pool.
- name string
- The deployment name.
- privateEndpoint DeploymentPrivate Endpoint 
- Configuration of the deployment's private endpoint.
- privateIps DeploymentPrivate Ip[] 
- The private IPv4 address associated with the deployment.
- projectId string
- project_id) The ID of the project the deployment is associated with.
- publicEndpoint DeploymentPublic Endpoint 
- Configuration of the deployment's public endpoint.
- quantization number
- The number of bits each model parameter should be quantized to
- region string
- region) The region in which the deployment is created.
- string[]
- The tags associated with the deployment.
- model_id str
- The model id used for the deployment.
- node_type str
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- accept_eula bool
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- max_size int
- The maximum size of the pool.
- min_size int
- The minimum size of the pool.
- name str
- The deployment name.
- private_endpoint DeploymentPrivate Endpoint Args 
- Configuration of the deployment's private endpoint.
- private_ips Sequence[DeploymentPrivate Ip Args] 
- The private IPv4 address associated with the deployment.
- project_id str
- project_id) The ID of the project the deployment is associated with.
- public_endpoint DeploymentPublic Endpoint Args 
- Configuration of the deployment's public endpoint.
- quantization int
- The number of bits each model parameter should be quantized to
- region str
- region) The region in which the deployment is created.
- Sequence[str]
- The tags associated with the deployment.
- modelId String
- The model id used for the deployment.
- nodeType String
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- acceptEula Boolean
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- maxSize Number
- The maximum size of the pool.
- minSize Number
- The minimum size of the pool.
- name String
- The deployment name.
- privateEndpoint Property Map
- Configuration of the deployment's private endpoint.
- privateIps List<Property Map>
- The private IPv4 address associated with the deployment.
- projectId String
- project_id) The ID of the project the deployment is associated with.
- publicEndpoint Property Map
- Configuration of the deployment's public endpoint.
- quantization Number
- The number of bits each model parameter should be quantized to
- region String
- region) The region in which the deployment is created.
- List<String>
- The tags associated with the deployment.
Outputs
All input properties are implicitly available as output properties. Additionally, the Deployment resource produces the following output properties:
- CreatedAt string
- The date and time of the creation of the deployment.
- Id string
- The provider-assigned unique ID for this managed resource.
- ModelName string
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- Size int
- The size of the pool.
- Status string
- The status of the deployment.
- UpdatedAt string
- The date and time of the last update of the deployment.
- CreatedAt string
- The date and time of the creation of the deployment.
- Id string
- The provider-assigned unique ID for this managed resource.
- ModelName string
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- Size int
- The size of the pool.
- Status string
- The status of the deployment.
- UpdatedAt string
- The date and time of the last update of the deployment.
- createdAt String
- The date and time of the creation of the deployment.
- id String
- The provider-assigned unique ID for this managed resource.
- modelName String
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- size Integer
- The size of the pool.
- status String
- The status of the deployment.
- updatedAt String
- The date and time of the last update of the deployment.
- createdAt string
- The date and time of the creation of the deployment.
- id string
- The provider-assigned unique ID for this managed resource.
- modelName string
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- size number
- The size of the pool.
- status string
- The status of the deployment.
- updatedAt string
- The date and time of the last update of the deployment.
- created_at str
- The date and time of the creation of the deployment.
- id str
- The provider-assigned unique ID for this managed resource.
- model_name str
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- size int
- The size of the pool.
- status str
- The status of the deployment.
- updated_at str
- The date and time of the last update of the deployment.
- createdAt String
- The date and time of the creation of the deployment.
- id String
- The provider-assigned unique ID for this managed resource.
- modelName String
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- size Number
- The size of the pool.
- status String
- The status of the deployment.
- updatedAt String
- The date and time of the last update of the deployment.
Look up Existing Deployment Resource
Get an existing Deployment resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.
public static get(name: string, id: Input<ID>, state?: DeploymentState, opts?: CustomResourceOptions): Deployment@staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        accept_eula: Optional[bool] = None,
        created_at: Optional[str] = None,
        max_size: Optional[int] = None,
        min_size: Optional[int] = None,
        model_id: Optional[str] = None,
        model_name: Optional[str] = None,
        name: Optional[str] = None,
        node_type: Optional[str] = None,
        private_endpoint: Optional[DeploymentPrivateEndpointArgs] = None,
        private_ips: Optional[Sequence[DeploymentPrivateIpArgs]] = None,
        project_id: Optional[str] = None,
        public_endpoint: Optional[DeploymentPublicEndpointArgs] = None,
        quantization: Optional[int] = None,
        region: Optional[str] = None,
        size: Optional[int] = None,
        status: Optional[str] = None,
        tags: Optional[Sequence[str]] = None,
        updated_at: Optional[str] = None) -> Deploymentfunc GetDeployment(ctx *Context, name string, id IDInput, state *DeploymentState, opts ...ResourceOption) (*Deployment, error)public static Deployment Get(string name, Input<string> id, DeploymentState? state, CustomResourceOptions? opts = null)public static Deployment get(String name, Output<String> id, DeploymentState state, CustomResourceOptions options)resources:  _:    type: scaleway:inference:Deployment    get:      id: ${id}- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- resource_name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- AcceptEula bool
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- CreatedAt string
- The date and time of the creation of the deployment.
- MaxSize int
- The maximum size of the pool.
- MinSize int
- The minimum size of the pool.
- ModelId string
- The model id used for the deployment.
- ModelName string
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- Name string
- The deployment name.
- NodeType string
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- PrivateEndpoint Pulumiverse.Scaleway. Inference. Inputs. Deployment Private Endpoint 
- Configuration of the deployment's private endpoint.
- PrivateIps List<Pulumiverse.Scaleway. Inference. Inputs. Deployment Private Ip> 
- The private IPv4 address associated with the deployment.
- ProjectId string
- project_id) The ID of the project the deployment is associated with.
- PublicEndpoint Pulumiverse.Scaleway. Inference. Inputs. Deployment Public Endpoint 
- Configuration of the deployment's public endpoint.
- Quantization int
- The number of bits each model parameter should be quantized to
- Region string
- region) The region in which the deployment is created.
- Size int
- The size of the pool.
- Status string
- The status of the deployment.
- List<string>
- The tags associated with the deployment.
- UpdatedAt string
- The date and time of the last update of the deployment.
- AcceptEula bool
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- CreatedAt string
- The date and time of the creation of the deployment.
- MaxSize int
- The maximum size of the pool.
- MinSize int
- The minimum size of the pool.
- ModelId string
- The model id used for the deployment.
- ModelName string
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- Name string
- The deployment name.
- NodeType string
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- PrivateEndpoint DeploymentPrivate Endpoint Args 
- Configuration of the deployment's private endpoint.
- PrivateIps []DeploymentPrivate Ip Args 
- The private IPv4 address associated with the deployment.
- ProjectId string
- project_id) The ID of the project the deployment is associated with.
- PublicEndpoint DeploymentPublic Endpoint Args 
- Configuration of the deployment's public endpoint.
- Quantization int
- The number of bits each model parameter should be quantized to
- Region string
- region) The region in which the deployment is created.
- Size int
- The size of the pool.
- Status string
- The status of the deployment.
- []string
- The tags associated with the deployment.
- UpdatedAt string
- The date and time of the last update of the deployment.
- acceptEula Boolean
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- createdAt String
- The date and time of the creation of the deployment.
- maxSize Integer
- The maximum size of the pool.
- minSize Integer
- The minimum size of the pool.
- modelId String
- The model id used for the deployment.
- modelName String
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- name String
- The deployment name.
- nodeType String
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- privateEndpoint DeploymentPrivate Endpoint 
- Configuration of the deployment's private endpoint.
- privateIps List<DeploymentPrivate Ip> 
- The private IPv4 address associated with the deployment.
- projectId String
- project_id) The ID of the project the deployment is associated with.
- publicEndpoint DeploymentPublic Endpoint 
- Configuration of the deployment's public endpoint.
- quantization Integer
- The number of bits each model parameter should be quantized to
- region String
- region) The region in which the deployment is created.
- size Integer
- The size of the pool.
- status String
- The status of the deployment.
- List<String>
- The tags associated with the deployment.
- updatedAt String
- The date and time of the last update of the deployment.
- acceptEula boolean
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- createdAt string
- The date and time of the creation of the deployment.
- maxSize number
- The maximum size of the pool.
- minSize number
- The minimum size of the pool.
- modelId string
- The model id used for the deployment.
- modelName string
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- name string
- The deployment name.
- nodeType string
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- privateEndpoint DeploymentPrivate Endpoint 
- Configuration of the deployment's private endpoint.
- privateIps DeploymentPrivate Ip[] 
- The private IPv4 address associated with the deployment.
- projectId string
- project_id) The ID of the project the deployment is associated with.
- publicEndpoint DeploymentPublic Endpoint 
- Configuration of the deployment's public endpoint.
- quantization number
- The number of bits each model parameter should be quantized to
- region string
- region) The region in which the deployment is created.
- size number
- The size of the pool.
- status string
- The status of the deployment.
- string[]
- The tags associated with the deployment.
- updatedAt string
- The date and time of the last update of the deployment.
- accept_eula bool
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- created_at str
- The date and time of the creation of the deployment.
- max_size int
- The maximum size of the pool.
- min_size int
- The minimum size of the pool.
- model_id str
- The model id used for the deployment.
- model_name str
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- name str
- The deployment name.
- node_type str
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- private_endpoint DeploymentPrivate Endpoint Args 
- Configuration of the deployment's private endpoint.
- private_ips Sequence[DeploymentPrivate Ip Args] 
- The private IPv4 address associated with the deployment.
- project_id str
- project_id) The ID of the project the deployment is associated with.
- public_endpoint DeploymentPublic Endpoint Args 
- Configuration of the deployment's public endpoint.
- quantization int
- The number of bits each model parameter should be quantized to
- region str
- region) The region in which the deployment is created.
- size int
- The size of the pool.
- status str
- The status of the deployment.
- Sequence[str]
- The tags associated with the deployment.
- updated_at str
- The date and time of the last update of the deployment.
- acceptEula Boolean
- Some models (e.g Meta Llama) require end-user license agreements. Set trueto accept.
- createdAt String
- The date and time of the creation of the deployment.
- maxSize Number
- The maximum size of the pool.
- minSize Number
- The minimum size of the pool.
- modelId String
- The model id used for the deployment.
- modelName String
- The model name used for the deployment. Model names can be found in Console or using Scaleway's CLI (scw inference model list)
- name String
- The deployment name.
- nodeType String
- The node type to use for the deployment. Node types can be found using Scaleway's CLI (scw inference node-type list)
- privateEndpoint Property Map
- Configuration of the deployment's private endpoint.
- privateIps List<Property Map>
- The private IPv4 address associated with the deployment.
- projectId String
- project_id) The ID of the project the deployment is associated with.
- publicEndpoint Property Map
- Configuration of the deployment's public endpoint.
- quantization Number
- The number of bits each model parameter should be quantized to
- region String
- region) The region in which the deployment is created.
- size Number
- The size of the pool.
- status String
- The status of the deployment.
- List<String>
- The tags associated with the deployment.
- updatedAt String
- The date and time of the last update of the deployment.
Supporting Types
DeploymentPrivateEndpoint, DeploymentPrivateEndpointArgs      
- DisableAuth bool
- Disable the authentication on the endpoint.
- Id string
- (Optional) The id of the public endpoint.
- PrivateNetwork stringId 
- The ID of the private network to use.
- Url string
- (Optional) The URL of the endpoint.
- DisableAuth bool
- Disable the authentication on the endpoint.
- Id string
- (Optional) The id of the public endpoint.
- PrivateNetwork stringId 
- The ID of the private network to use.
- Url string
- (Optional) The URL of the endpoint.
- disableAuth Boolean
- Disable the authentication on the endpoint.
- id String
- (Optional) The id of the public endpoint.
- privateNetwork StringId 
- The ID of the private network to use.
- url String
- (Optional) The URL of the endpoint.
- disableAuth boolean
- Disable the authentication on the endpoint.
- id string
- (Optional) The id of the public endpoint.
- privateNetwork stringId 
- The ID of the private network to use.
- url string
- (Optional) The URL of the endpoint.
- disable_auth bool
- Disable the authentication on the endpoint.
- id str
- (Optional) The id of the public endpoint.
- private_network_ strid 
- The ID of the private network to use.
- url str
- (Optional) The URL of the endpoint.
- disableAuth Boolean
- Disable the authentication on the endpoint.
- id String
- (Optional) The id of the public endpoint.
- privateNetwork StringId 
- The ID of the private network to use.
- url String
- (Optional) The URL of the endpoint.
DeploymentPrivateIp, DeploymentPrivateIpArgs      
DeploymentPublicEndpoint, DeploymentPublicEndpointArgs      
- DisableAuth bool
- Disable the authentication on the endpoint.
- Id string
- (Optional) The id of the public endpoint.
- IsEnabled bool
- Enable or disable public endpoint.
- Url string
- (Optional) The URL of the endpoint.
- DisableAuth bool
- Disable the authentication on the endpoint.
- Id string
- (Optional) The id of the public endpoint.
- IsEnabled bool
- Enable or disable public endpoint.
- Url string
- (Optional) The URL of the endpoint.
- disableAuth Boolean
- Disable the authentication on the endpoint.
- id String
- (Optional) The id of the public endpoint.
- isEnabled Boolean
- Enable or disable public endpoint.
- url String
- (Optional) The URL of the endpoint.
- disableAuth boolean
- Disable the authentication on the endpoint.
- id string
- (Optional) The id of the public endpoint.
- isEnabled boolean
- Enable or disable public endpoint.
- url string
- (Optional) The URL of the endpoint.
- disable_auth bool
- Disable the authentication on the endpoint.
- id str
- (Optional) The id of the public endpoint.
- is_enabled bool
- Enable or disable public endpoint.
- url str
- (Optional) The URL of the endpoint.
- disableAuth Boolean
- Disable the authentication on the endpoint.
- id String
- (Optional) The id of the public endpoint.
- isEnabled Boolean
- Enable or disable public endpoint.
- url String
- (Optional) The URL of the endpoint.
Import
Functions can be imported using, {region}/{id}, as shown below:
bash
$ pulumi import scaleway:inference/deployment:Deployment deployment fr-par/11111111-1111-1111-1111-111111111111
To learn more about importing existing cloud resources, see Importing resources.
Package Details
- Repository
- scaleway pulumiverse/pulumi-scaleway
- License
- Apache-2.0
- Notes
- This Pulumi package is based on the scalewayTerraform Provider.
 
