Class MachineSpec (3.74.0)

Specification of a single machine.

Protobuf type google.cloud.aiplatform.v1beta1.MachineSpec

The number of accelerators to attach to the machine.

int32 accelerator_count = 3;

Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.

.google.cloud.aiplatform.v1beta1.AcceleratorType accelerator_type = 2 [(.google.api.field_behavior) = IMMUTABLE];

Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.

.google.cloud.aiplatform.v1beta1.AcceleratorType accelerator_type = 2 [(.google.api.field_behavior) = IMMUTABLE];

Optional. Immutable. The Nvidia GPU partition size.

When specified, the requested accelerators will be partitioned into smaller GPU partitions. For example, if the request is for 8 units of NVIDIA A100 GPUs, and gpu_partition_size="1g.10gb", the service will create 8 * 7 = 56 partitioned MIG instances.

The partition size must be a value supported by the requested accelerator. Refer to Nvidia GPU Partitioning for the available partition sizes.

If set, the accelerator_count should be set to 1.

string gpu_partition_size = 7 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OPTIONAL];

Optional. Immutable. The Nvidia GPU partition size.

When specified, the requested accelerators will be partitioned into smaller GPU partitions. For example, if the request is for 8 units of NVIDIA A100 GPUs, and gpu_partition_size="1g.10gb", the service will create 8 * 7 = 56 partitioned MIG instances.

The partition size must be a value supported by the requested accelerator. Refer to Nvidia GPU Partitioning for the available partition sizes.

If set, the accelerator_count should be set to 1.

string gpu_partition_size = 7 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OPTIONAL];

Immutable. 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.

string machine_type = 1 [(.google.api.field_behavior) = IMMUTABLE];

Immutable. 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.

string machine_type = 1 [(.google.api.field_behavior) = IMMUTABLE];

Optional. Immutable. The number of nodes per replica for multihost GPU deployments.

int32 multihost_gpu_node_count = 6 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OPTIONAL];

Optional. Immutable. Configuration controlling how this resource pool consumes reservation.

.google.cloud.aiplatform.v1beta1.ReservationAffinity reservation_affinity = 5 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OPTIONAL];

Optional. Immutable. Configuration controlling how this resource pool consumes reservation.

.google.cloud.aiplatform.v1beta1.ReservationAffinity reservation_affinity = 5 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OPTIONAL];

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

string tpu_topology = 4 [(.google.api.field_behavior) = IMMUTABLE];

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

string tpu_topology = 4 [(.google.api.field_behavior) = IMMUTABLE];

Optional. Immutable. Configuration controlling how this resource pool consumes reservation.

.google.cloud.aiplatform.v1beta1.ReservationAffinity reservation_affinity = 5 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OPTIONAL];