Inference Component Compute Resource Requirements
data class InferenceComponentComputeResourceRequirements(val maxMemoryRequiredInMb: Int? = null, val minMemoryRequiredInMb: Int? = null, val numberOfAcceleratorDevicesRequired: Double? = null, val numberOfCpuCoresRequired: Double? = null)
Properties
Link copied to clipboard
The maximum MB of memory to allocate to run a model that you assign to an inference component.
Link copied to clipboard
The minimum MB of memory to allocate to run a model that you assign to an inference component.
Link copied to clipboard
The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and AWS Inferentia.
Link copied to clipboard
The number of CPU cores to allocate to run a model that you assign to an inference component.