Skip to main content
Ctrl+K

Flyte

  • User guide
  • Tutorials
  • Integrations
  • Deployment guide
  • API reference
    • Community
    • Flyte
  • GitHub
  • Slack
  • Flyte
  • User guide
  • Tutorials
  • Integrations
  • Deployment guide
  • API reference
  • Community
  • Flyte
  • GitHub
  • Slack
  • Flyte

API reference

  • flytekit
    • Overview
      • Model Files
      • Authoring Structure
      • Control Plane: FlyteRemote
      • Execution Time Support
      • Command Line Interfaces and Clients
    • Core Flytekit
      • flytekit.task
      • flytekit.workflow
      • flytekit.kwtypes
      • flytekit.current_context
      • flytekit.ExecutionParameters
      • flytekit.FlyteContext
      • flytekit.map_task
      • flytekit.core.workflow.ImperativeWorkflow
      • flytekit.core.node_creation.create_node
      • flytekit.core.promise.NodeOutput
      • flytekit.FlyteContextManager
      • flytekit.conditional
      • flytekit.TaskMetadata
      • flytekit.Resources
      • flytekit.WorkflowFailurePolicy
      • flytekit.PodTemplate
      • flytekit.dynamic
      • flytekit.approve
      • flytekit.sleep
      • flytekit.wait_for_input
      • flytekit.CronSchedule
      • flytekit.FixedRate
      • flytekit.Email
      • flytekit.PagerDuty
      • flytekit.Slack
      • flytekit.get_reference_entity
      • flytekit.LaunchPlanReference
      • flytekit.TaskReference
      • flytekit.WorkflowReference
      • flytekit.reference_task
      • flytekit.reference_workflow
      • flytekit.reference_launch_plan
      • flytekit.SQLTask
      • flytekit.ContainerTask
      • flytekit.PythonFunctionTask
      • flytekit.PythonInstanceTask
      • flytekit.LaunchPlan
      • flytekit.Secret
      • flytekit.SecurityContext
      • flytekit.AuthRole
      • flytekit.Labels
      • flytekit.Annotations
      • flytekit.WorkflowExecutionPhase
      • flytekit.Blob
      • flytekit.BlobMetadata
      • flytekit.Literal
      • flytekit.Scalar
      • flytekit.LiteralType
      • flytekit.BlobType
      • flytekit.HashMethod
      • flytekit.Artifact
      • flytekit.Description
      • flytekit.Documentation
      • flytekit.SourceCode
    • Configuration
      • flytekit.configuration.Config
      • flytekit.configuration.Image
      • flytekit.configuration.ImageConfig
      • flytekit.configuration.SerializationSettings
      • flytekit.configuration.FastSerializationSettings
      • flytekit.configuration.PlatformConfig
      • flytekit.configuration.StatsConfig
      • flytekit.configuration.SecretsConfig
      • flytekit.configuration.S3Config
      • flytekit.configuration.GCSConfig
      • flytekit.configuration.DataConfig
    • ImageSpec
      • flytekit.image_spec.ImageSpec
    • Remote Access
      • flytekit.remote.remote.FlyteRemote
      • flytekit.remote.remote.Options
      • flytekit.remote.entities.FlyteTask
      • flytekit.remote.entities.FlyteWorkflow
      • flytekit.remote.entities.FlyteLaunchPlan
      • flytekit.remote.entities.FlyteNode
      • flytekit.remote.entities.FlyteTaskNode
      • flytekit.remote.entities.FlyteWorkflowNode
      • flytekit.remote.executions.FlyteWorkflowExecution
      • flytekit.remote.executions.FlyteTaskExecution
      • flytekit.remote.executions.FlyteNodeExecution
    • Clients
      • flytekit.clients.friendly.SynchronousFlyteClient
      • flytekit.clients.raw.RawSynchronousFlyteClient
    • Unit Testing
      • flytekit.testing.patch
      • flytekit.testing.task_mock
    • Specifying Accelerators
      • flytekit.extras.accelerators.BaseAccelerator
      • flytekit.extras.accelerators.GPUAccelerator
      • flytekit.extras.accelerators.MultiInstanceGPUAccelerator
      • flytekit.extras.accelerators.A10G
      • flytekit.extras.accelerators.L4
      • flytekit.extras.accelerators.K80
      • flytekit.extras.accelerators.M60
      • flytekit.extras.accelerators.P4
      • flytekit.extras.accelerators.P100
      • flytekit.extras.accelerators.T4
      • flytekit.extras.accelerators.V100
      • flytekit.extras.accelerators.A100
      • flytekit.extras.accelerators.A100_80GB
    • Extending Flytekit
      • flytekit.extend.get_serializable
      • flytekit.extend.context_manager
      • flytekit.extend.IgnoreOutputs
      • flytekit.extend.ExecutionState
      • flytekit.extend.Image
      • flytekit.extend.ImageConfig
      • flytekit.extend.Interface
      • flytekit.extend.Promise
      • flytekit.extend.TaskPlugins
      • flytekit.extend.DictTransformer
      • flytekit.extend.T
      • flytekit.extend.TypeEngine
      • flytekit.extend.TypeTransformer
      • flytekit.extend.PythonCustomizedContainerTask
      • flytekit.extend.ExecutableTemplateShimTask
      • flytekit.extend.ShimTaskExecutor
    • Flyte Deck
      • flytekit.deck.Deck
      • flytekit.deck.TopFrameRenderer
      • flytekit.deck.MarkdownRenderer
      • flytekit.deck.SourceCodeRenderer
    • Plugin API reference
      • AWS Athena
        • flytekitplugins.athena.AthenaConfig
        • flytekitplugins.athena.AthenaTask
      • AWS Batch
        • flytekitplugins.awsbatch.AWSBatchConfig
      • Google Bigquery
        • flytekitplugins.bigquery.BigQueryConfig
        • flytekitplugins.bigquery.BigQueryTask
        • flytekitplugins.bigquery.BigQueryAgent
      • Dask
        • flytekitplugins.dask.Dask
        • flytekitplugins.dask.Scheduler
        • flytekitplugins.dask.WorkerGroup
      • Deck standard
        • flytekitplugins.deck.BoxRenderer
        • flytekitplugins.deck.FrameProfilingRenderer
        • flytekitplugins.deck.GanttChartRenderer
        • flytekitplugins.deck.ImageRenderer
        • flytekitplugins.deck.MarkdownRenderer
        • flytekitplugins.deck.SourceCodeRenderer
        • flytekitplugins.deck.TableRenderer
      • Dolt standard
        • flytekitplugins.dolt.DoltConfig
        • flytekitplugins.dolt.DoltTable
        • flytekitplugins.dolt.DoltTableNameTransformer
      • Great expectations
        • flytekitplugins.great_expectations.BatchRequestConfig
        • flytekitplugins.great_expectations.GreatExpectationsFlyteConfig
        • flytekitplugins.great_expectations.GreatExpectationsTask
        • flytekitplugins.great_expectations.GreatExpectationsType
      • Hive
        • flytekitplugins.hive.HiveConfig
        • flytekitplugins.hive.HiveSelectTask
        • flytekitplugins.hive.HiveTask
      • Pod
      • KF MPI
        • flytekitplugins.kfmpi.MPIJob
      • KF Pytorch
        • flytekitplugins.kfpytorch.PyTorch
        • flytekitplugins.kfpytorch.Elastic
      • KF Tensorflow
        • flytekitplugins.kftensorflow.TfJob
      • Modin
        • flytekitplugins.modin.ModinPandasDataFrameTransformer
      • Pandera
        • flytekitplugins.pandera.PanderaPandasTransformer
        • flytekitplugins.pandera.PandasReportRenderer
        • flytekitplugins.pandera.ValidationConfig
      • Papermill
        • flytekitplugins.papermill.NotebookTask
        • flytekitplugins.papermill.record_outputs
      • PERIAN
        • flytekitplugins.perian_job.PerianAgent
        • flytekitplugins.perian_job.PerianConfig
        • flytekitplugins.perian_job.PerianTask
      • Snowflake
        • flytekitplugins.snowflake.SnowflakeConfig
        • flytekitplugins.snowflake.SnowflakeTask
        • flytekitplugins.snowflake.SnowflakeAgent
      • Spark
        • flytekitplugins.spark.new_spark_session
        • flytekitplugins.spark.ParquetToSparkDecodingHandler
        • flytekitplugins.spark.Spark
        • flytekitplugins.spark.SparkDataFrameSchemaReader
        • flytekitplugins.spark.SparkDataFrameSchemaWriter
        • flytekitplugins.spark.SparkDataFrameTransformer
      • SQLAlchemy
        • flytekitplugins.sqlalchemy.SQLAlchemyConfig
        • flytekitplugins.sqlalchemy.SQLAlchemyDefaultImages
        • flytekitplugins.sqlalchemy.SQLAlchemyTask
      • ONNX PyTorch
        • flytekitplugins.onnxpytorch.PyTorch2ONNXConfig
        • flytekitplugins.onnxpytorch.PyTorch2ONNX
      • ONNX TensorFlow
        • flytekitplugins.onnxtensorflow.TensorFlow2ONNXConfig
        • flytekitplugins.onnxtensorflow.TensorFlow2ONNX
      • ONNX ScikitLearn
        • flytekitplugins.onnxscikitlearn.ScikitLearn2ONNXConfig
        • flytekitplugins.onnxscikitlearn.ScikitLearn2ONNX
      • Ray
        • flytekitplugins.ray.HeadNodeConfig
        • flytekitplugins.ray.RayJobConfig
        • flytekitplugins.ray.WorkerNodeConfig
      • DBT
        • flytekitplugins.dbt.DBTRun
        • flytekitplugins.dbt.DBTTest
        • flytekitplugins.dbt.BaseDBTInput
        • flytekitplugins.dbt.BaseDBTOutput
        • flytekitplugins.dbt.DBTRunInput
        • flytekitplugins.dbt.DBTRunOutput
        • flytekitplugins.dbt.DBTTestInput
        • flytekitplugins.dbt.DBTTestOutput
      • Vaex
        • flytekitplugins.vaex.VaexDataFrameToParquetEncodingHandler
        • flytekitplugins.vaex.ParquetToVaexDataFrameDecodingHandler
      • MLflow
        • flytekitplugins.mlflow.mlflow_autolog
      • DuckDB
        • flytekitplugins.duckdb.DuckDBQuery
      • SageMaker Inference
        • flytekitplugins.awssagemaker_inference.BotoAgent
        • flytekitplugins.awssagemaker_inference.BotoTask
        • flytekitplugins.awssagemaker_inference.SageMakerModelTask
        • flytekitplugins.awssagemaker_inference.SageMakerEndpointConfigTask
        • flytekitplugins.awssagemaker_inference.SageMakerEndpointAgent
        • flytekitplugins.awssagemaker_inference.SageMakerEndpointTask
        • flytekitplugins.awssagemaker_inference.SageMakerDeleteEndpointConfigTask
        • flytekitplugins.awssagemaker_inference.SageMakerDeleteEndpointTask
        • flytekitplugins.awssagemaker_inference.SageMakerDeleteModelTask
        • flytekitplugins.awssagemaker_inference.SageMakerInvokeEndpointTask
        • flytekitplugins.awssagemaker_inference.create_sagemaker_deployment
        • flytekitplugins.awssagemaker_inference.delete_sagemaker_deployment
      • OpenAI
        • flytekitplugins.openai.BatchEndpointAgent
        • flytekitplugins.openai.BatchEndpointTask
        • flytekitplugins.openai.BatchResult
        • flytekitplugins.openai.DownloadJSONFilesTask
        • flytekitplugins.openai.UploadJSONLFileTask
        • flytekitplugins.openai.OpenAIFileConfig
        • flytekitplugins.openai.create_batch
        • flytekitplugins.openai.ChatGPTAgent
        • flytekitplugins.openai.ChatGPTTask
      • Inference
        • flytekitplugins.inference.NIM
        • flytekitplugins.inference.NIMSecrets
        • flytekitplugins.inference.Model
        • flytekitplugins.inference.Ollama
      • Neptune
        • flytekitplugins.neptune.neptune_init_run
      • Weights & Biases
        • flytekitplugins.wandb.wandb_init
    • Custom Tasks
      • flytekit.core.base_task.kwtypes
      • flytekit.core.base_task.PythonTask
      • flytekit.core.base_task.Task
      • flytekit.core.base_task.TaskResolverMixin
      • flytekit.core.base_task.IgnoreOutputs
      • flytekit.core.python_function_task.PythonFunctionTask
      • flytekit.core.python_function_task.PythonInstanceTask
      • Shell Task
        • flytekit.extras.tasks.shell.ShellTask
        • flytekit.extras.tasks.shell.OutputLocation
      • SQLite3 Task
        • flytekit.extras.sqlite3.task.SQLite3Task
        • flytekit.extras.sqlite3.task.SQLite3Config
    • Custom Types
      • Flytekit StructuredDataset
        • flytekit.types.structured.StructuredDataset
        • flytekit.types.structured.StructuredDatasetDecoder
        • flytekit.types.structured.StructuredDatasetEncoder
      • Flytekit File Type
        • flytekit.types.file.FlyteFile
        • flytekit.types.file.HDF5EncodedFile
        • flytekit.types.file.HTMLPage
        • flytekit.types.file.JoblibSerializedFile
        • flytekit.types.file.JPEGImageFile
        • flytekit.types.file.PDFFile
        • flytekit.types.file.PNGImageFile
        • flytekit.types.file.PythonPickledFile
        • flytekit.types.file.PythonNotebook
        • flytekit.types.file.SVGImageFile
      • Flytekit Directory Type
        • flytekit.types.directory.FlyteDirectory
        • flytekit.types.directory.TensorboardLogs
        • flytekit.types.directory.TFRecordsDirectory
      • Flytekit Iterator Type
        • flytekit.types.iterator.FlyteIterator
        • flytekit.types.iterator.JSON
      • PyTorch Type
        • flytekit.extras.pytorch.PyTorchCheckpoint
        • flytekit.extras.pytorch.PyTorchCheckpointTransformer
        • flytekit.extras.pytorch.PyTorchModuleTransformer
        • flytekit.extras.pytorch.PyTorchTensorTransformer
      • TensorFlow Type
        • flytekit.extras.tensorflow.TensorFlowRecordFileTransformer
        • flytekit.extras.tensorflow.TensorFlowRecordsDirTransformer
      • Sklearn Type
        • flytekit.extras.sklearn.SklearnEstimatorTransformer
    • Experimental Features
    • Pyflyte CLI
    • Flytekit Contribution Guide
  • flytectl
    • Overview
    • CLI Entrypoint
    • Verbs
      • flytectl create
      • flytectl completion
      • flytectl get
      • flytectl update
      • flytectl delete
      • flytectl register
      • flytectl config
      • flytectl compile
      • flytectl sandbox
      • flytectl demo
      • flytectl version
      • flytectl upgrade
    • Nouns
      • Project
        • flytectl create project
        • flytectl get project
        • flytectl update project
      • Execution
        • flytectl create execution
        • flytectl get execution
        • flytectl update execution
        • flytectl delete execution
      • Workflow
        • flytectl get workflow
        • flytectl update workflow-meta
      • Task
        • flytectl get task
        • flytectl update task-meta
      • Task resource attribute
        • flytectl get task-resource-attribute
        • flytectl update task-resource-attribute
        • flytectl delete task-resource-attribute
      • Cluster resource attribute
        • flytectl get cluster-resource-attribute
        • flytectl delete cluster-resource-attribute
        • flytectl update cluster-resource-attribute
      • Execution cluster label
        • flytectl get execution-cluster-label
        • flytectl update execution-cluster-label
        • flytectl delete execution-cluster-label
      • Execution queue attribute
        • flytectl get execution-queue-attribute
        • flytectl delete execution-queue-attribute
        • flytectl update execution-queue-attribute
      • Plugin override
        • flytectl get plugin-override
        • flytectl update plugin-override
        • flytectl delete plugin-override
      • Launchplan
        • flytectl get launchplan
        • flytectl update launchplan
        • flytectl update launchplan-meta
      • Workflow execution config
        • flytectl get workflow-execution-config
        • flytectl update workflow-execution-config
        • flytectl delete workflow-execution-config
      • Examples
        • flytectl register examples
      • Files
        • flytectl register files
      • Config
        • flytectl config validate
        • flytectl config init
        • flytectl config docs
        • flytectl config discover
      • Sandbox
        • flytectl sandbox start
        • flytectl sandbox status
        • flytectl sandbox teardown
        • flytectl sandbox exec
      • Demo
        • flytectl demo start
        • flytectl demo status
        • flytectl demo teardown
        • flytectl demo exec
        • flytectl demo reload
    • Contributing Guide
  • flyteidl
    • Flyte Admin Service entities
      • Protocol Documentation
    • Core Flyte language specification
      • Protocol Documentation
    • Flyte Data Catalog Service
      • Protocol Documentation
    • Flyte Internal and External Eventing interface
      • Protocol Documentation
    • Flyte Task Plugins
      • Protocol Documentation
    • REST and gRPC interface for the Flyte Admin Service
      • Protocol Documentation
    • Contributing to FlyteIDL
  • API reference
  • Flytekit API Reference
  • Plugin API reference
  • Model Inference reference

Model Inference reference#

Tags: Integration, Serving, Inference

NIM

NIMSecrets

Model

Represents the configuration for a model used in a Kubernetes pod template.

Ollama

previous

flytekitplugins.openai.ChatGPTTask

next

flytekitplugins.inference.NIM
Edit on GitHub
Copyright © 2024, Flyte authors