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

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

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

Performance range for a model deployment.

Inheritance

object > PerformanceRange

Namespace

Google.Cloud.GkeRecommender.V1

Assembly

Google.Cloud.GkeRecommender.V1.dll

Constructors

PerformanceRange()

public PerformanceRange()

PerformanceRange(PerformanceRange)

public PerformanceRange(PerformanceRange other)
Parameter
Name Description
other PerformanceRange

Properties

NtpotRange

public MillisecondRange NtpotRange { get; set; }

Output only. The range of NTPOT (Normalized Time Per Output Token) in milliseconds. NTPOT is the request latency normalized by the number of output tokens, measured as request_latency / total_output_tokens.

Property Value
Type Description
MillisecondRange

ThroughputOutputRange

public TokensPerSecondRange ThroughputOutputRange { get; set; }

Output only. The range of throughput in output tokens per second. This is measured as total_output_tokens_generated_by_server / elapsed_time_in_seconds.

Property Value
Type Description
TokensPerSecondRange

TtftRange

public MillisecondRange TtftRange { get; set; }

Output only. The range of TTFT (Time To First Token) in milliseconds. TTFT is the time it takes to generate the first token for a request.

Property Value
Type Description
MillisecondRange