Dgxc-lepton
flytekitplugins-dgxc-lepton
A professional Flytekit plugin that enables seamless deployment and management of AI inference endpoints using Lepton AI infrastructure within Flyte workflows.
pip install flytekitplugins-dgxc-leptonQuick Start(example, may need adjustment)
pip install flytekitplugins-dgxc-lepton
from flytekit import task, workflow
from flytekitplugins.dgxc_lepton import lepton_endpoint_deployment_task, lepton_endpoint_deletion_task, LeptonEndpointConfig, LeptonEndpointDeploymentTask
@task
def my_task() -> None:
lepton_endpoint_deployment_task(...)
@workflow
def my_workflow() -> None:
my_task()Available Imports (11)
Task for Dgxc-lepton.
from flytekitplugins.dgxc_lepton import lepton_endpoint_deployment_task
Task for Dgxc-lepton.
from flytekitplugins.dgxc_lepton import lepton_endpoint_deletion_task
Complete configuration for Lepton AI endpoint deployment.
extends dataclass — configuration or data structure for plugin setup
from flytekitplugins.dgxc_lepton import LeptonEndpointConfig
Task for Dgxc-lepton.
extends PythonTask — a flyte task that can be used in workflows
from flytekitplugins.dgxc_lepton import LeptonEndpointDeploymentTask
Task for Dgxc-lepton.
extends PythonTask — a flyte task that can be used in workflows
from flytekitplugins.dgxc_lepton import LeptonEndpointDeletionTask
Supported endpoint types for Lepton AI.
extends Enum — enumeration of predefined options
from flytekitplugins.dgxc_lepton import EndpointType
Unified environment variable configuration for Lepton deployments.
extends dataclass — configuration or data structure for plugin setup
from flytekitplugins.dgxc_lepton import EnvironmentConfig
Mount configuration for Lepton deployments.
extends dataclass — configuration or data structure for plugin setup
from flytekitplugins.dgxc_lepton import MountReader
Unified scaling configuration that enforces only one scaling type.
extends dataclass — configuration or data structure for plugin setup
from flytekitplugins.dgxc_lepton import ScalingConfig
Supported scaling types for Lepton AI.
extends Enum — enumeration of predefined options
from flytekitplugins.dgxc_lepton import ScalingType
Unified endpoint configuration that enforces only one endpoint type.
extends dataclass — configuration or data structure for plugin setup
from flytekitplugins.dgxc_lepton import EndpointEngineConfig
Dependencies
Related Plugins
SGLang
Serve large language models using SGLang with Flyte Apps.
vLLM
Serve large language models using vLLM with Flyte Apps.
Inference
Serve models natively in Flyte tasks using inference providers like NIM, Ollama, and others.
ONNX PyTorch
This plugin allows you to generate ONNX models from your PyTorch models.
