Reference documentation and code samples for the GKE Recommender V1 API class Google::Cloud::GkeRecommender::V1::Profile.
A profile containing information about a model deployment.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#accelerator_type
def accelerator_type() -> ::String
Returns
-
(::String) — Output only. The accelerator type. Expected format:
nvidia-h100-80gb.
#instance_type
def instance_type() -> ::String
Returns
-
(::String) — Output only. The instance type. Expected format:
a2-highgpu-1g.
#model_server_info
def model_server_info() -> ::Google::Cloud::GkeRecommender::V1::ModelServerInfo
Returns
- (::Google::Cloud::GkeRecommender::V1::ModelServerInfo) — Output only. The model server configuration. Use GkeInferenceQuickstart.FetchProfiles to find valid configurations.
#performance_stats
def performance_stats() -> ::Array<::Google::Cloud::GkeRecommender::V1::PerformanceStats>
Returns
- (::Array<::Google::Cloud::GkeRecommender::V1::PerformanceStats>) — Output only. The performance statistics for this profile.
#resources_used
def resources_used() -> ::Google::Cloud::GkeRecommender::V1::ResourcesUsed
Returns
- (::Google::Cloud::GkeRecommender::V1::ResourcesUsed) — Output only. The resources used by the model deployment.
#tpu_topology
def tpu_topology() -> ::String
Returns
- (::String) — Output only. The TPU topology (if applicable).