Reference documentation and code samples for the Google Cloud Gke Recommender V1 Client class PerformanceRequirements.
Performance requirements for a profile and or model deployment.
Generated from protobuf message google.cloud.gkerecommender.v1.PerformanceRequirements
Namespace
Google \ Cloud \ GkeRecommender \ V1Methods
__construct
Constructor.
| Parameters | |
|---|---|
| Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ target_ntpot_milliseconds |
int
Optional. The target Normalized Time Per Output Token (NTPOT) in milliseconds. NTPOT is calculated as |
↳ target_ttft_milliseconds |
int
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. |
↳ target_cost |
Cost
Optional. The target cost for running a profile's model server. If not provided, this requirement will not be enforced. |
getTargetNtpotMilliseconds
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.
| Returns | |
|---|---|
| Type | Description |
int |
|
hasTargetNtpotMilliseconds
clearTargetNtpotMilliseconds
setTargetNtpotMilliseconds
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.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getTargetTtftMilliseconds
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.
| Returns | |
|---|---|
| Type | Description |
int |
|
hasTargetTtftMilliseconds
clearTargetTtftMilliseconds
setTargetTtftMilliseconds
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.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getTargetCost
Optional. The target cost for running a profile's model server. If not provided, this requirement will not be enforced.
| Returns | |
|---|---|
| Type | Description |
Cost|null |
|
hasTargetCost
clearTargetCost
setTargetCost
Optional. The target cost for running a profile's model server. If not provided, this requirement will not be enforced.
| Parameter | |
|---|---|
| Name | Description |
var |
Cost
|
| Returns | |
|---|---|
| Type | Description |
$this |
|