Skip to main content

Module clients.dai_engine_profile.dai_engine_profile

Functions​

from_api_object ​

def from_api_object(api_object: h2o_engine_manager.gen.model.v1_dai_engine_profile.V1DAIEngineProfile) ‑> DAIEngineProfile

Classes​

DAIEngineProfile​

class DAIEngineProfile(cpu_constraint: h2o_engine_manager.clients.constraint.profile_constraint_numeric.ProfileConstraintNumeric, gpu_constraint: h2o_engine_manager.clients.constraint.profile_constraint_numeric.ProfileConstraintNumeric, memory_bytes_constraint: h2o_engine_manager.clients.constraint.profile_constraint_numeric.ProfileConstraintNumeric, storage_bytes_constraint: h2o_engine_manager.clients.constraint.profile_constraint_numeric.ProfileConstraintNumeric, max_idle_duration_constraint: h2o_engine_manager.clients.constraint.profile_constraint_duration.ProfileConstraintDuration, max_running_duration_constraint: h2o_engine_manager.clients.constraint.profile_constraint_duration.ProfileConstraintDuration, config_editability: h2o_engine_manager.clients.dai_engine_profile.config_editability.ConfigEditability, name: str = '', display_name: str = '', priority: int = 0, enabled: bool = True, assigned_oidc_roles_enabled: bool = True, assigned_oidc_roles: Optional[List[str]] = None, max_running_engines: Optional[int] = None, max_non_interaction_duration: Optional[str] = None, max_unused_duration: Optional[str] = None, configuration_override: Optional[Dict[str, str]] = None, base_configuration: Optional[Dict[str, str]] = None, yaml_pod_template_spec: str = '', yaml_gpu_tolerations: str = '', triton_enabled: bool = False, create_time: Optional[datetime.datetime] = None, update_time: Optional[datetime.datetime] = None, creator: str = '', updater: str = '', creator_display_name: str = '', updater_display_name: str = '')

DAIEngineProfile represents a set of values that are used for DAIEngine.

DAIEngineProfile represents a set of values that are used for DAIEngine.

Args​
cpu_constraint
Constraint for each DAIEngine's cpu that uses this profile.
gpu_constraint
Constraint for each DAIEngine's gpu that uses this profile.
memory_bytes_constraint
Constraint for each DAIEngine's memory_bytes that uses this profile.
storage_bytes_constraint
Constraint for each DAIEngine's storage_bytes that uses this profile.
max_idle_duration_constraint
Constraint for each DAIEngine's max_idle_duration that uses this profile.
max_running_duration_constraint
Constraint for each DAIEngine's max_running_duration that uses this profile.
config_editability
Specifies the behavior of DAIEngine.config editability when DAIEngine is using this profile.
name
Resource name. Format "daiEngineProfiles/*".
display_name
Human-readable name.
priority
Priority of the DAIEngineProfile. Lower value means higher priority. Priority is NOT a unique value (any two DAIEngineProfiles can have the same priority value).
enabled
When set to true, the DAIEngineProfile is enabled and can be used in DAIEngine. When set to false, the DAIEngineProfile is disabled and cannot be used in any DAIEngine.
assigned_oidc_roles_enabled
When set to true, the assigned_oidc_roles field is verified when a user uses this profile.
assigned_oidc_roles
List of OIDC roles assigned to this DAIEngineProfile. When profile has assigned some OIDC roles and verification of this list is enabled (assigned_oidc_roles_enabled=true), then this profile can be used only by users who have assigned at least one role from this list.
max_running_engines
Maximum number of DAIEngines per user that can be running when using this DAIEngineProfile.
max_non_interaction_duration
Max non-interation duration applied on all DAIEngines that use this profile.
max_unused_duration
Max unused duration applied on all DAIEngines that use this profile.
configuration_override
configuration_override is applied on top of all other configurations when creating the final configuration that is passed to the DAI server.
base_configuration
base configuration forms the basis of the final configuration that is passed to the DAI server.
yaml_pod_template_spec
YAML representation of custom PodTemplateSpec. Definition of PodTemplateSpec: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.27/#podtemplatespec-v1-coreWhen specified, then it is applied for each DAIEngine that uses this profile. PodTemplateSpec describes what will be applied on top of a regular DriverlessAI pod before it is created. This template is merged into DriverlessAI default pod using StrategicMergePatch method (it overrides the default pod). More info about StrategicMergePatch: https://kubernetes.io/docs/tasks/manage-kubernetes-objects/update-api-object-kubectl-patch/
yaml_gpu_tolerations
YAML representation of custom GPU Tolerations. Definition of one Toleration: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.27/#toleration-v1-coreWhen specified, then it is applied for each DAIEngine that uses this profile. GPUTolerations sets DriverlessAI's pod.spec.tolerations in case DAIEngine has GPU > 0. This will override any tolerations defined in yaml_pod_template_spec.PodSpec.Tolerations field.
triton_enabled
True when DAI built-in Triton inference server is enabled, false when it is disabled.
create_time
Time when the DAIEngineProfile was created.
update_time
Time when the DAIEngineProfile was last updated.
creator
Name of entity that created the DAIEngineProfile.
updater
Name of entity that last updated the DAIEngineProfile.
creator_display_name
Human-readable name of entity that created the DAIEngineProfile.
updater_display_name
Human-readable name of entity that last updated the DAIEngineProfile.

Methods​

to_api_object ​

def to_api_object(self) ‑> h2o_engine_manager.gen.model.v1_dai_engine_profile.V1DAIEngineProfile

to_resource ​

def to_resource(self) ‑> h2o_engine_manager.gen.model.required_dai_engine_profile_resource.RequiredDAIEngineProfileResource
Feedback