create_compute_quota ¶

def create_compute_quota(
    self,
    *,
    config_overrides: Optional[SageMakerClientConfig] = None,
    name: Optional["capo_sagemaker.types.entity_name.EntityName"] = None,
    description: Optional[
        "capo_sagemaker.types.entity_description.EntityDescription"
    ] = None,
    cluster_arn: Optional["capo_sagemaker.types.cluster_arn.ClusterArn"] = None,
    compute_quota_config: Optional[
        "capo_sagemaker.types.compute_quota_config.ComputeQuotaConfig"
    ] = None,
    compute_quota_target: Optional[
        "capo_sagemaker.types.compute_quota_target.ComputeQuotaTarget"
    ] = None,
    activation_state: Optional[
        "capo_sagemaker.types.activation_state.ActivationState"
    ] = None,
    tags: Optional["capo_sagemaker.types.tag_list.TagList"] = None,
) -> (
    "capo_sagemaker.types.create_compute_quota_response.CreateComputeQuotaResponse"
):
    """<p>Create compute allocation definition. This defines how compute is allocated, shared, and borrowed for specified entities. Specifically, how to lend and borrow idle compute and assign a fair-share weight to the specified entities.</p>

    Args:
        name: <p>The name of the compute allocation definition. The name must be unique within the SageMaker AI HyperPod cluster specified by <code>ClusterArn</code>. You can use the same name in other clusters within a Region or across Regions.</p>
        description: <p>Description of the compute allocation definition.</p>
        cluster_arn: <p>ARN of the cluster.</p>
        compute_quota_config: <p>Configuration of the compute allocation definition. This includes the resource sharing option, and the setting to preempt low priority tasks.</p>
        compute_quota_target: <p>The target entity to allocate compute resources to.</p>
        activation_state: <p>The state of the compute allocation being described. Use to enable or disable compute allocation.</p> <p>Default is <code>Enabled</code>.</p>
        tags: <p>Tags of the compute allocation definition.</p>

    Raises:
        capo_sagemaker.errors.conflict_exception.ConflictException: <p>There was a conflict when you attempted to modify a SageMaker entity such as an <code>Experiment</code> or <code>Artifact</code>.</p>
        capo_sagemaker.errors.resource_limit_exceeded.ResourceLimitExceeded: <p> You have exceeded an SageMaker resource limit. For example, you might have too many training jobs created. </p>
        capo_sagemaker.errors.UnknownServiceError: The service returned an error code this client does not model.
    """

    def _handler(
        req: "OperationRequest[capo_sagemaker.types.create_compute_quota_request.CreateComputeQuotaRequest]",
    ) -> OperationResponse[
        "capo_sagemaker.types.create_compute_quota_response.CreateComputeQuotaResponse"
    ]:
        import capo_sagemaker._operations.sage_maker.create_compute_quota

        output, http_response = (
            capo_sagemaker._operations.sage_maker.create_compute_quota.create_compute_quota(
                req.options, req.input
            )
        )
        return OperationResponse(output=output, response=http_response)

    interceptors_, options_ = self.operation_options(
        config_overrides, OperationLogging("CreateComputeQuota")
    )
    input_: capo_sagemaker.types.create_compute_quota_request.CreateComputeQuotaRequest = {}
    if name is not None:
        input_["name"] = name
    if description is not None:
        input_["description"] = description
    if cluster_arn is not None:
        input_["cluster_arn"] = cluster_arn
    if compute_quota_config is not None:
        input_["compute_quota_config"] = compute_quota_config
    if compute_quota_target is not None:
        input_["compute_quota_target"] = compute_quota_target
    if activation_state is not None:
        input_["activation_state"] = activation_state
    if tags is not None:
        input_["tags"] = tags

    response = execute_pipeline(
        OperationRequest(input=input_, options=options_),
        handler=_handler,
        interceptors=list(interceptors_),
    )
    response.response.close()
    return response.output