GKE Recommender v1 API - Class PerformanceRequirements (1.0.0-beta01)

public sealed class PerformanceRequirements : IMessage<PerformanceRequirements>, IEquatable<PerformanceRequirements>, IDeepCloneable<PerformanceRequirements>, IBufferMessage, IMessage

Reference documentation and code samples for the GKE Recommender v1 API class PerformanceRequirements.

Performance requirements for a profile and or model deployment.

Inheritance

object > PerformanceRequirements

Namespace

Google.Cloud.GkeRecommender.V1

Assembly

Google.Cloud.GkeRecommender.V1.dll

Constructors

PerformanceRequirements()

public PerformanceRequirements()

PerformanceRequirements(PerformanceRequirements)

public PerformanceRequirements(PerformanceRequirements other)
Parameter
Name Description
other PerformanceRequirements

Properties

HasTargetNtpotMilliseconds

public bool HasTargetNtpotMilliseconds { get; }

Gets whether the "target_ntpot_milliseconds" field is set

Property Value
Type Description
bool

HasTargetTtftMilliseconds

public bool HasTargetTtftMilliseconds { get; }

Gets whether the "target_ttft_milliseconds" field is set

Property Value
Type Description
bool

TargetCost

public Cost TargetCost { get; set; }

Optional. The target cost for running a profile's model server. If not provided, this requirement will not be enforced.

Property Value
Type Description
Cost

TargetNtpotMilliseconds

public int TargetNtpotMilliseconds { get; set; }

Optional. The target Normalized Time Per Output Token (NTPOT) in milliseconds. NTPOT is calculated as request_latency / total_output_tokens. If not provided, this target will not be enforced.

Property Value
Type Description
int

TargetTtftMilliseconds

public int TargetTtftMilliseconds { get; set; }

Optional. The target Time To First Token (TTFT) in milliseconds. TTFT is the time it takes to generate the first token for a request. If not provided, this target will not be enforced.

Property Value
Type Description
int