public static final class PerformanceStats.Builder extends GeneratedMessageV3.Builder<PerformanceStats.Builder> implements PerformanceStatsOrBuilderPerformance statistics for a model deployment.
Protobuf type google.cloud.gkerecommender.v1.PerformanceStats
Inheritance
Object > AbstractMessageLite.Builder<MessageType,BuilderType> > AbstractMessage.Builder<BuilderType> > GeneratedMessageV3.Builder > PerformanceStats.BuilderImplements
PerformanceStatsOrBuilderStatic Methods
getDescriptor()
public static final Descriptors.Descriptor getDescriptor()| Returns | |
|---|---|
| Type | Description |
Descriptor |
|
Methods
addAllCost(Iterable<? extends Cost> values)
public PerformanceStats.Builder addAllCost(Iterable<? extends Cost> values)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
values |
Iterable<? extends com.google.cloud.gkerecommender.v1.Cost> |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
addCost(Cost value)
public PerformanceStats.Builder addCost(Cost value)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
value |
Cost |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
addCost(Cost.Builder builderForValue)
public PerformanceStats.Builder addCost(Cost.Builder builderForValue)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
builderForValue |
Cost.Builder |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
addCost(int index, Cost value)
public PerformanceStats.Builder addCost(int index, Cost value)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameters | |
|---|---|
| Name | Description |
index |
int |
value |
Cost |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
addCost(int index, Cost.Builder builderForValue)
public PerformanceStats.Builder addCost(int index, Cost.Builder builderForValue)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameters | |
|---|---|
| Name | Description |
index |
int |
builderForValue |
Cost.Builder |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
addCostBuilder()
public Cost.Builder addCostBuilder()Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
Cost.Builder |
|
addCostBuilder(int index)
public Cost.Builder addCostBuilder(int index)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
index |
int |
| Returns | |
|---|---|
| Type | Description |
Cost.Builder |
|
addRepeatedField(Descriptors.FieldDescriptor field, Object value)
public PerformanceStats.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)| Parameters | |
|---|---|
| Name | Description |
field |
FieldDescriptor |
value |
Object |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
build()
public PerformanceStats build()| Returns | |
|---|---|
| Type | Description |
PerformanceStats |
|
buildPartial()
public PerformanceStats buildPartial()| Returns | |
|---|---|
| Type | Description |
PerformanceStats |
|
clear()
public PerformanceStats.Builder clear()| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
clearCost()
public PerformanceStats.Builder clearCost()Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
clearField(Descriptors.FieldDescriptor field)
public PerformanceStats.Builder clearField(Descriptors.FieldDescriptor field)| Parameter | |
|---|---|
| Name | Description |
field |
FieldDescriptor |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
clearNtpotMilliseconds()
public PerformanceStats.Builder clearNtpotMilliseconds()Output only. The Normalized Time Per Output Token (NTPOT) in milliseconds. This is the request latency normalized by the number of output tokens, measured as request_latency / total_output_tokens.
int32 ntpot_milliseconds = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
This builder for chaining. |
clearOneof(Descriptors.OneofDescriptor oneof)
public PerformanceStats.Builder clearOneof(Descriptors.OneofDescriptor oneof)| Parameter | |
|---|---|
| Name | Description |
oneof |
OneofDescriptor |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
clearOutputTokensPerSecond()
public PerformanceStats.Builder clearOutputTokensPerSecond()Output only. The number of output tokens per second. This is the throughput measured as total_output_tokens_generated_by_server / elapsed_time_in_seconds.
int32 output_tokens_per_second = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
This builder for chaining. |
clearQueriesPerSecond()
public PerformanceStats.Builder clearQueriesPerSecond()Output only. The number of queries per second. Note: This metric can vary widely based on context length and may not be a reliable measure of LLM throughput.
float queries_per_second = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
This builder for chaining. |
clearTtftMilliseconds()
public PerformanceStats.Builder clearTtftMilliseconds()Output only. The Time To First Token (TTFT) in milliseconds. This is the time it takes to generate the first token for a request.
int32 ttft_milliseconds = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
This builder for chaining. |
clone()
public PerformanceStats.Builder clone()| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
getCost(int index)
public Cost getCost(int index)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
index |
int |
| Returns | |
|---|---|
| Type | Description |
Cost |
|
getCostBuilder(int index)
public Cost.Builder getCostBuilder(int index)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
index |
int |
| Returns | |
|---|---|
| Type | Description |
Cost.Builder |
|
getCostBuilderList()
public List<Cost.Builder> getCostBuilderList()Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
List<Builder> |
|
getCostCount()
public int getCostCount()Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
int |
|
getCostList()
public List<Cost> getCostList()Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
List<Cost> |
|
getCostOrBuilder(int index)
public CostOrBuilder getCostOrBuilder(int index)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
index |
int |
| Returns | |
|---|---|
| Type | Description |
CostOrBuilder |
|
getCostOrBuilderList()
public List<? extends CostOrBuilder> getCostOrBuilderList()Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
List<? extends com.google.cloud.gkerecommender.v1.CostOrBuilder> |
|
getDefaultInstanceForType()
public PerformanceStats getDefaultInstanceForType()| Returns | |
|---|---|
| Type | Description |
PerformanceStats |
|
getDescriptorForType()
public Descriptors.Descriptor getDescriptorForType()| Returns | |
|---|---|
| Type | Description |
Descriptor |
|
getNtpotMilliseconds()
public int getNtpotMilliseconds()Output only. The Normalized Time Per Output Token (NTPOT) in milliseconds. This is the request latency normalized by the number of output tokens, measured as request_latency / total_output_tokens.
int32 ntpot_milliseconds = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
int |
The ntpotMilliseconds. |
getOutputTokensPerSecond()
public int getOutputTokensPerSecond()Output only. The number of output tokens per second. This is the throughput measured as total_output_tokens_generated_by_server / elapsed_time_in_seconds.
int32 output_tokens_per_second = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
int |
The outputTokensPerSecond. |
getQueriesPerSecond()
public float getQueriesPerSecond()Output only. The number of queries per second. Note: This metric can vary widely based on context length and may not be a reliable measure of LLM throughput.
float queries_per_second = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
float |
The queriesPerSecond. |
getTtftMilliseconds()
public int getTtftMilliseconds()Output only. The Time To First Token (TTFT) in milliseconds. This is the time it takes to generate the first token for a request.
int32 ttft_milliseconds = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Returns | |
|---|---|
| Type | Description |
int |
The ttftMilliseconds. |
internalGetFieldAccessorTable()
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()| Returns | |
|---|---|
| Type | Description |
FieldAccessorTable |
|
isInitialized()
public final boolean isInitialized()| Returns | |
|---|---|
| Type | Description |
boolean |
|
mergeFrom(PerformanceStats other)
public PerformanceStats.Builder mergeFrom(PerformanceStats other)| Parameter | |
|---|---|
| Name | Description |
other |
PerformanceStats |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
public PerformanceStats.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)| Parameters | |
|---|---|
| Name | Description |
input |
CodedInputStream |
extensionRegistry |
ExtensionRegistryLite |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
| Exceptions | |
|---|---|
| Type | Description |
IOException |
|
mergeFrom(Message other)
public PerformanceStats.Builder mergeFrom(Message other)| Parameter | |
|---|---|
| Name | Description |
other |
Message |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
mergeUnknownFields(UnknownFieldSet unknownFields)
public final PerformanceStats.Builder mergeUnknownFields(UnknownFieldSet unknownFields)| Parameter | |
|---|---|
| Name | Description |
unknownFields |
UnknownFieldSet |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
removeCost(int index)
public PerformanceStats.Builder removeCost(int index)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
index |
int |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
setCost(int index, Cost value)
public PerformanceStats.Builder setCost(int index, Cost value)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameters | |
|---|---|
| Name | Description |
index |
int |
value |
Cost |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
setCost(int index, Cost.Builder builderForValue)
public PerformanceStats.Builder setCost(int index, Cost.Builder builderForValue)Output only. The cost of running the model deployment.
repeated .google.cloud.gkerecommender.v1.Cost cost = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameters | |
|---|---|
| Name | Description |
index |
int |
builderForValue |
Cost.Builder |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
setField(Descriptors.FieldDescriptor field, Object value)
public PerformanceStats.Builder setField(Descriptors.FieldDescriptor field, Object value)| Parameters | |
|---|---|
| Name | Description |
field |
FieldDescriptor |
value |
Object |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
setNtpotMilliseconds(int value)
public PerformanceStats.Builder setNtpotMilliseconds(int value)Output only. The Normalized Time Per Output Token (NTPOT) in milliseconds. This is the request latency normalized by the number of output tokens, measured as request_latency / total_output_tokens.
int32 ntpot_milliseconds = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
value |
intThe ntpotMilliseconds to set. |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
This builder for chaining. |
setOutputTokensPerSecond(int value)
public PerformanceStats.Builder setOutputTokensPerSecond(int value)Output only. The number of output tokens per second. This is the throughput measured as total_output_tokens_generated_by_server / elapsed_time_in_seconds.
int32 output_tokens_per_second = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
value |
intThe outputTokensPerSecond to set. |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
This builder for chaining. |
setQueriesPerSecond(float value)
public PerformanceStats.Builder setQueriesPerSecond(float value)Output only. The number of queries per second. Note: This metric can vary widely based on context length and may not be a reliable measure of LLM throughput.
float queries_per_second = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
value |
floatThe queriesPerSecond to set. |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
This builder for chaining. |
setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
public PerformanceStats.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)| Parameters | |
|---|---|
| Name | Description |
field |
FieldDescriptor |
index |
int |
value |
Object |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|
setTtftMilliseconds(int value)
public PerformanceStats.Builder setTtftMilliseconds(int value)Output only. The Time To First Token (TTFT) in milliseconds. This is the time it takes to generate the first token for a request.
int32 ttft_milliseconds = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];
| Parameter | |
|---|---|
| Name | Description |
value |
intThe ttftMilliseconds to set. |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
This builder for chaining. |
setUnknownFields(UnknownFieldSet unknownFields)
public final PerformanceStats.Builder setUnknownFields(UnknownFieldSet unknownFields)| Parameter | |
|---|---|
| Name | Description |
unknownFields |
UnknownFieldSet |
| Returns | |
|---|---|
| Type | Description |
PerformanceStats.Builder |
|