gpuPartitionSize property

String gpuPartitionSize
final

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.

Implementation

final String gpuPartitionSize;