public class DescribeModelResponse
extends java.lang.Object
| Modifier and Type | Class and Description |
|---|---|
static class |
DescribeModelResponse.Worker
A class that holds workers information.
|
| Constructor and Description |
|---|
DescribeModelResponse()
Constructs a
DescribeModelResponse instance. |
| Modifier and Type | Method and Description |
|---|---|
void |
addWorker(int id,
long startTime,
boolean isRunning,
int gpuId)
Adds worker to the worker list.
|
int |
getBatchSize()
Returns the batch size.
|
int |
getMaxBatchDelay()
Returns the maximum delay in milliseconds to aggregate a batch.
|
int |
getMaxIdleTime()
Returns the maximum idle time for worker threads.
|
int |
getMaxWorkers()
Returns the desired maximum number of workers.
|
int |
getMinWorkers()
Returns the desired minimum number of workers.
|
java.lang.String |
getModelName()
Returns the model name.
|
java.lang.String |
getModelUrl()
Returns the model URL.
|
java.lang.String |
getStatus()
Returns the model's status.
|
java.util.List<DescribeModelResponse.Worker> |
getWorkers()
Returns all workers information of the model.
|
boolean |
isLoadedAtStartup()
Returns if the models was loaded at startup.
|
void |
setBatchSize(int batchSize)
Sets the batch size.
|
void |
setLoadedAtStartup(boolean loadedAtStartup)
Sets the load at startup status.
|
void |
setMaxBatchDelay(int maxBatchDelay)
Sets the maximum delay in milliseconds to aggregate a batch.
|
void |
setMaxIdleTime(int maxIdleTime)
Sets the max idle time for worker threads.
|
void |
setMaxWorkers(int maxWorkers)
Sets the desired maximum number of workers.
|
void |
setMinWorkers(int minWorkers)
Sets the desired minimum number of workers.
|
void |
setModelName(java.lang.String modelName)
Sets the model name.
|
void |
setModelUrl(java.lang.String modelUrl)
Sets the model URL.
|
void |
setStatus(java.lang.String status)
Sets the model's status.
|
public DescribeModelResponse()
DescribeModelResponse instance.public java.lang.String getModelName()
public void setModelName(java.lang.String modelName)
modelName - the model namepublic boolean isLoadedAtStartup()
true if the models was loaded at startuppublic void setLoadedAtStartup(boolean loadedAtStartup)
loadedAtStartup - true if the models was loaded at startuppublic java.lang.String getModelUrl()
public void setModelUrl(java.lang.String modelUrl)
modelUrl - the model URLpublic int getMinWorkers()
public void setMinWorkers(int minWorkers)
minWorkers - the desired minimum number of workerspublic int getMaxWorkers()
public void setMaxWorkers(int maxWorkers)
maxWorkers - the desired maximum number of workerspublic int getBatchSize()
public void setBatchSize(int batchSize)
batchSize - the batch sizepublic int getMaxBatchDelay()
public void setMaxBatchDelay(int maxBatchDelay)
maxBatchDelay - the maximum delay in milliseconds to aggregate a batchpublic java.lang.String getStatus()
public void setStatus(java.lang.String status)
status - the model's statuspublic void setMaxIdleTime(int maxIdleTime)
maxIdleTime - the time a worker thread can be idle before scaling down.public int getMaxIdleTime()
public java.util.List<DescribeModelResponse.Worker> getWorkers()
public void addWorker(int id,
long startTime,
boolean isRunning,
int gpuId)
id - the worker's IDstartTime - the worker's start timeisRunning - true if worker is runninggpuId - the GPU id assigned to the worker, -1 for CPU