AiEndpointWithModelGardenDeploymentDeployConfigDedicatedResourcesMachineSpec class

Constructors

AiEndpointWithModelGardenDeploymentDeployConfigDedicatedResourcesMachineSpec({Input<int?>? acceleratorCount, Input<String?>? acceleratorType, Input<String?>? machineType, Input<int?>? multihostGpuNodeCount, Input<AiEndpointWithModelGardenDeploymentDeployConfigDedicatedResourcesMachineSpecReservationAffinity?>? reservationAffinity, Input<String?>? tpuTopology})

Creates a new AiEndpointWithModelGardenDeploymentDeployConfigDedicatedResourcesMachineSpec. acceleratorCount The number of accelerators to attach to the machine. acceleratorType Possible values: machineType The type of the machine. multihostGpuNodeCount The number of nodes per replica for multihost GPU deployments. reservationAffinity A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a tpuTopology The topology of the TPUs. Corresponds to the TPU topologies available from

const

AiEndpointWithModelGardenDeploymentDeployConfigDedicatedResourcesMachineSpec.fromMap(Map<String, dynamic> map)

factory

Properties

acceleratorCount → Input<int?>?

The number of accelerators to attach to the machine.

final

acceleratorType → Input<String?>?

Possible values: ACCELERATOR_TYPE_UNSPECIFIED NVIDIA_TESLA_K80 NVIDIA_TESLA_P100 NVIDIA_TESLA_V100 NVIDIA_TESLA_P4 NVIDIA_TESLA_T4 NVIDIA_TESLA_A100 NVIDIA_A100_80GB NVIDIA_L4 NVIDIA_H100_80GB NVIDIA_H100_MEGA_80GB NVIDIA_H200_141GB NVIDIA_B200 TPU_V2 TPU_V3 TPU_V4_POD TPU_V5_LITEPOD

final

hashCode → int

The hash code for this object.

no setter, inherited

machineType → Input<String?>?

The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.

final

multihostGpuNodeCount → Input<int?>?

The number of nodes per replica for multihost GPU deployments.

final

reservationAffinity → Input<AiEndpointWithModelGardenDeploymentDeployConfigDedicatedResourcesMachineSpecReservationAffinity?>?

A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. Structure is documented below.

final

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

tpuTopology → Input<String?>?

The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").

final

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toMap() → Map<String, dynamic>

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited