Skip to content

InferenceComponentComputeResourceRequirements

Source code in docs_src/capo_sagemaker/types/inference_component_compute_resource_requirements.py
class InferenceComponentComputeResourceRequirements(TypedDict, closed=True):
    number_of_cpu_cores_required: NotRequired[
        "capo_sagemaker.types.number_of_cpu_cores.NumberOfCpuCores"
    ]
    """<p>The number of CPU cores to allocate to run a model that you assign to an inference component.</p>"""
    number_of_accelerator_devices_required: NotRequired[
        "capo_sagemaker.types.number_of_accelerator_devices.NumberOfAcceleratorDevices"
    ]
    """<p>The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and Amazon Web Services Inferentia.</p>"""
    min_memory_required_in_mb: NotRequired[
        "capo_sagemaker.types.memory_in_mb.MemoryInMb"
    ]
    """<p>The minimum MB of memory to allocate to run a model that you assign to an inference component.</p>"""
    max_memory_required_in_mb: NotRequired[
        "capo_sagemaker.types.memory_in_mb.MemoryInMb"
    ]
    """<p>The maximum MB of memory to allocate to run a model that you assign to an inference component.</p>"""

max_memory_required_in_mb instance-attribute

max_memory_required_in_mb: NotRequired[MemoryInMb]

The maximum MB of memory to allocate to run a model that you assign to an inference component.

min_memory_required_in_mb instance-attribute

min_memory_required_in_mb: NotRequired[MemoryInMb]

The minimum MB of memory to allocate to run a model that you assign to an inference component.

number_of_accelerator_devices_required instance-attribute

number_of_accelerator_devices_required: NotRequired[NumberOfAcceleratorDevices]

The number of accelerators to allocate to run a model that you assign to an inference component. Accelerators include GPUs and Amazon Web Services Inferentia.

number_of_cpu_cores_required instance-attribute

number_of_cpu_cores_required: NotRequired[NumberOfCpuCores]

The number of CPU cores to allocate to run a model that you assign to an inference component.