Reference documentation and code samples for the Google Cloud Gke Recommender V1 Client class PerformanceRange.
Performance range for a model deployment.
Generated from protobuf message google.cloud.gkerecommender.v1.PerformanceRange
Namespace
Google \ Cloud \ GkeRecommender \ V1Methods
__construct
Constructor.
| Parameters | |
|---|---|
| Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ throughput_output_range |
TokensPerSecondRange
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. |
↳ ttft_range |
MillisecondRange
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. |
↳ ntpot_range |
MillisecondRange
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. |
getThroughputOutputRange
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.
| Returns | |
|---|---|
| Type | Description |
TokensPerSecondRange|null |
|
hasThroughputOutputRange
clearThroughputOutputRange
setThroughputOutputRange
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.
| Parameter | |
|---|---|
| Name | Description |
var |
TokensPerSecondRange
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getTtftRange
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.
| Returns | |
|---|---|
| Type | Description |
MillisecondRange|null |
|
hasTtftRange
clearTtftRange
setTtftRange
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.
| Parameter | |
|---|---|
| Name | Description |
var |
MillisecondRange
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getNtpotRange
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.
| Returns | |
|---|---|
| Type | Description |
MillisecondRange|null |
|
hasNtpotRange
clearNtpotRange
setNtpotRange
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.
| Parameter | |
|---|---|
| Name | Description |
var |
MillisecondRange
|
| Returns | |
|---|---|
| Type | Description |
$this |
|